Dr. Muthoni Masinde holds doctorate, masters and bachelors degrees in computer science from the University of Cape Town, the Vrije Universiteit Brussel and the University of Nairobi respectively. She is an academic member of staff at the School of Computing and Informatics, University of Nairobi, Kenya and also works as a consultant academic researcher at the Central University of Technology, South Africa. Her research involves developing ICT-based solutions to droughts and climate change using wireless sensor networks and mobile phones. Dr. Masinde’s most recent research output is a novel bridge dubbed itiki (acronym for Information Technology and Indigenous Knowledge with Intelligence) that was realised in form of a drought early warning system. The bridge integrates African indigenous knowledge (IK) on droughts with the scientific drought forecasting approaches.
Low Internet coverage and lack of electricity in the rural areas of the developing countries of A... more Low Internet coverage and lack of electricity in the rural areas of the developing countries of Africa make use of computer-based solutions a big challenge, yet there is dire need of such applications in these areas. Luckily, most of these countries have reported impressive adoption levels of mobile phones[3], a phenomenon that is now creating a paradigm shift; computing is slowly moving from the traditional PC to the phone. Coincidentally, advancements in the Smartphone technology have produced such powerful gadgets that can ably compete with PCs of the 21st century. Today, for less than US$ 400, one can acquire a Smartphone equipped with; 1000MHz clock speed, 512MiB(ROM+RAM), several data links (CSD, HSCSD, GPRS, EDGE), Wireless local-area network (WLAN) among other features[6]. With this kind of computing power, computer analysts/programmers can now develop both scientific and commercial applications to address numerous challenging facing poor people in the developing countries of Africa.
ABSTRACT The popularity and the high processing power of today's smart phones have presen... more ABSTRACT The popularity and the high processing power of today's smart phones have presented computer scientists with a fertile platform on which to implement grid computing for mobile phones. Such grids will not require much investment since they are designed to make use of `idle' power on already existing phones. This is because most smart phone users only use their phones for a few minutes or a few hours every day and yet, these phones are powered up 24/7. These kinds of grids are most favorable to developing countries where the penetration of mobile phone exceeds other forms of ICTs. Once in place, the grids can then be utilized to run the much-needed applications such e-health, e-education and drought prediction. In this paper, we present MobiGrid, a middleware for mobile phone grid that is part of a larger research project that aims at integrating mobile phones and sensors to come up with a drought predication tool for use in the developing countries. MobiGrid is an API on which distributed applications can be built. Unlike the rest of grid middleware solutions, the uniqueness of our approach lies in the fact that the middleware is for mobile phones environment.
Page 1. Survey on DNS Configurations, Interdependencies, Resilience and Security for *.ke Domains... more Page 1. Survey on DNS Configurations, Interdependencies, Resilience and Security for *.ke Domains James G. Kagwe School of Computing University of Nairobi Nairobi, Kenya kagwejg@gmail.com Muthoni Masinde Hasso ...
The Annual Conference on WWW Applications - 213, Sep 10, 2013
"Internet of Things (IoT) is both an evolutionary and revolutionary paradigm which since its birt... more "Internet of Things (IoT) is both an evolutionary and revolutionary paradigm which since its birth in the late 2008, has received considerable attention especially from researchers. There are a couple of definitions and visions of IoT that can be deduced; the most common vision being the ‘“anywhere, anytime, by anyone and anything”(the “4A vision”) while most common definition is: “IoT is a network of interconnected things/objects that are uniquely addressable”. In the traditional set up, the ‘things’ could be the inherently digital items such as Radio Frequency Identifiers (RFID), mobile phones, motor vehicles and computers; in the ideal IoT paradigm however, the ‘things’ include human beings, plants, domestic/wild animals, basically ‘anything’. Equipped with sensing, on-board processing, communication and storage capabilities, sensors are powerful devices used to autonomously gather and disseminate information on virtually any physical object/process and occurrence of events. The greatest potential of sensors is however realised within wireless sensor networks (WSNs) which are made up of a large number of sensors (commonly referred to as nodes) that cooperatively monitor large environments. It is widely believed that the ‘things’ that really unleashes the power of IoT are the WSNs. Self-configurability, autonomy and easiness of deployment are the salient features of WSNs that make them the main candidates for ‘pervasive computing’ and indeed the 4As vision of IoT paradigm.
Implementation of weather forecasting systems in many Sub-Saharan Africa (SSA) countries is hampered by among other things, inadequate coverage by weather stations. Ideally, when deployed in their hundreds, WSNs-based weather meters can mitigate this by capturing weather parameters at micro-level. However, the reality is different, the cost of sensor boards is still prohibitive; boards cost between 100 to 800 Euros (Bagula et al. 2012). The wireless sensors communication protocols only allow coverage of between 100 and 300M and Global System for Mobile Communications (GSM) in SSA is not reliable enough to support interruption-free communication. Even then, with a functioning WSNs-based drought monitoring system, there is no guarantee that the people (especially the small-scale farmers) that need it most in SSA will utilise the information for an array of reasons that are documented in literature (Masinde 2012). For example, studies reveal that over 80% of farmers in some parts of Ethiopia, Kenya, Zambia and Zimbabwe relied on Indigenous Knowledge Forecasts (IKFs)(Mugabe et al. 2010). This is where Internet of Things (IoT) comes in; instead of creating a homogenous drought forecasting system made up of sensors, a system made up of heterogeneous weather information sources (such as sensors, mobile phones, conventional weather stations, indigenous drought forecasters (rainmakers), mobile phones, smart billboards and so on) would suffice. Though IoT is yet to be realised in the commercial/industrial and business worlds, to address this, a generic service-oriented 5-layered architecture for implementing IoT applications is presented in this paper. This architecture is then used to realise a droughts early warning system. This work therefore affirms that despite the current challenges facing IoT’s real-life implementation, it is possible to implement a simple IoT application to addresses the unique problem of droughts in SSA.
"
Though most factors that trigger droughts cannot be prevented, accurate, relevant and timely fore... more Though most factors that trigger droughts cannot be prevented, accurate, relevant and timely forecasts can be used to mitigate their impacts. Drought forecasts must define the droughts severity, onset, cessation, duration and spatial distribution. Given the high probability of droughts occurrence in Kenya, her heavy reliance on rain-fed agriculture and lack of effective drought mitigation strategies, the Country is highly vulnerable to impacts of droughts. Current drought forecasting approaches used in Kenya are not able to provide short and long term forecasts and they fall short of providing the severity of the drought. In this paper, a combination of Artificial Neural Networks and Effective Drought Index is presented as a potential candidate for addressing these drawbacks. This is demonstrated using forecasting models that were built using weather data for thirty years for four weather stations (representing 3 agro-ecological zones) in Kenya. Experiments varying various input/output combinations were carried out and drought forecasting network models were implemented in MATLAB’s Neural Network Toolbox. The models incorporate forecasted rainfall values in order to mitigate for unexpected extreme climate variations. With accuracies as high as 98%, the solution is a great enhancement to the solutions currently in use in Kenya.
Proceedings of the TU Kaleidoscope conference, Kyoto, Japan, 22-24 April 2013
Mbeere is in Eastern Kenya and it has an average of 550 mm annual rainfall and therefore classifi... more Mbeere is in Eastern Kenya and it has an average of 550 mm annual rainfall and therefore classified under Arid and Semi-Arid Lands. It has fragile ecosystems, unfavorable climate, poor infrastructure and historical marginalization; the perennial natural disasters here are droughts. Of importance to this paper is the fact that despite its vast area of 2,093 km2, there is no single weather station serving the area. The main source of livelihood is rain-fed marginal farming and livestock keeping by small-scale and peasant farmers who rely mostly on the indigenous knowledge of seasons in making cropping decisions. ITIKI; acronym for Information Technology and Indigenous Knowledge with Intelligence is a bridge that integrates indigenous drought forecasting approach into the scientific drought forecasting approach. ITIKI, a framework initiated by the authors of this paper was adopted and adapted from the word itiki which is the name used among the Mbeere people to refer to an indigenous bridge used for decades to go across rivers. ITIKI makes use of mobile phones, wireless sensor networks and artificial intelligence to downscale weather/drought forecasts to individual farmers. ITIKI implementation project in Mbeere commenced in August 2012; this paper describes the implementation roadmap for this project.
Proceedings of the IST-Africa 2013, Nairobi, 29 - 31 May 2013, May 29, 2013
Like most other developing countries of Africa, Kenya’s rain-fed agriculture is the backbone of t... more Like most other developing countries of Africa, Kenya’s rain-fed agriculture is the backbone of the economy. As such, the Country’s economy and weather are so intertwined that a good season means healthy economy and famine, and death otherwise. The status of weather forecasting in Kenya is rather wanting partly because the data used is collected from very sparse network of professional weather stations. Procuring and maintaining these stations is a costly affair for the Country still struggling to meet basic needs for her population. Developments in sensor technology have resulted in affordable and sustainable weatherboards that can operate as mini-weather stations. Though not as good as professional weather stations, these boards can be used to compliment the networks of weather stations, hence improving the accuracy of weather forecasts produced by the Kenya Meteorological Department. We present SenseWeather, a weather monitoring system that we developed using Agriculture Boards from Libelium. In this paper, we describe the design, sensor calibration and deployment of SenseWeather.
Droughts have become chronic in Africa; especially in the Sub-Saharan Africa (Szöllösi-Nagy, 1999... more Droughts have become chronic in Africa; especially in the Sub-Saharan Africa (Szöllösi-Nagy, 1999) where they have resulted in the unending problem of food insecurity. Overall, droughts cause the greatest havoc in Africa; they for example accounted for over 90% of people affected by natural disasters in Africa between 2000 and 2009 (RedCross, 2010). Second in the list were floods (a related disaster), which accounted for a mere 8%. Further, during the same period (2000 to 2009), Africa contributed 46% of all droughts recorded. The complex nature of droughts’ onset-termination has made it acquire the title; “the creeping disaster” (Mishra and Singh, 2010) and unlike other disasters, drought’s effects continue to be felt long after its termination and it spans all aspects of human life. Agriculture still remains one of the key pillars of most economies in Africa. The situation is made worse by the fact that a big chunk (over 70%) comes from vulnerable rain-fed small scale farming operating in fragile environments that are ecologically, geographically and economically marginalized (ISDR, 2008). Farmers in this category would definitely benefit more from drought prediction solutions that are designed with their involvement. These farmers are more interested in customised forecast information that can reliably inform them about the onset, cessation, and intra-seasonal variations in order to reach decisions such as what, when and how to plant/harvest.
The most commonly used form of forecasts used in most countries in Africa is the Seasonal Climate Forecasts (SCFs). Research (Ziervogel and Opere, 2010) has shown that SCFs are too supply-driven and are too ‘course’ to have any relevance at a local community level. The terminologies (e.g. below and normal level) and formats used do not make much sense to most farmers. Furthermore, the mode (websites, radio/television broadcasts and print media) of dissemination does not reach the targeted audience. Consequently, these farmers continue to rely on forecasts that are based on indigenous knowledge (IKFs). For instance, it is in realization of this fact that an initiative (http://www.africa-adapt.net/aa/ProjectOverview.aspx?PID=PUXVdbXh9bM%3D) aimed at integrating SCFs with IKFs was piloted in Kenya. The integration was geared towards maximizing the strengths of the two (SCFs and IKFs) and by extension to improve the adoption of weather forecasts by small-scale farmers. Started in September 2008, the project brought together meteorologists and the Nganyi indigenous knowledge forecasters to build ‘reconciliations’ between SCFs and IKFs. The reconciled forecasts were carried out for 7 seasons between 2007 and 2011 and results disseminated through the locally available (existing) communication channels such as chief barazas and churches. The outcome of the project was rated ‘very good’ by the two parties.
There has been a sharp increase in publications in the area of Indigenous Knowledge (IK) in Africa especially in South Africa where tens of research projects are funded through the National Research Foundation (Loubser, 2005). Despite this encouraging trend, publications in the category of weather/droughts/climate-variation prediction are still rare. For instance, in a recent study (Njiraine et al, 2010) on IK research in Kenya and South Africa, publications directly and indirectly touching on this topic were those under agriculture and environment categories. Unlike other categories such as culture (with 41.2% for Kenya and 31% for South Africa), these (agriculture and environment) categories had minimal representations of 11.5% and 7.5% for agriculture and 12% and 6.9% for environment; the percentages are for Kenya and South Africa respectively. Generally, publications under IK on drought/weather management in Africa ((ISDR, 2008), (Ziervogel and Opere, 2010), (Ajibade and Shokemi, 2003), (Roos and Dewald, 2010), (Steiner, 2008) and (UNEP, 2011)) reveal that communities in Africa used more or less common approaches in predicting drought/weather. They observed changing seasons as well as lunar cycles (shape/position of the moon and patterns of stars). They also observed the natural environment (behavior of animals/birds and looks of some plants) and like the weathermen of today, IK also involved studying the meteorological parameters such as air/temperature intensity, clouds colour/direction and wind direction. Religious beliefs and myths also contributed greatly to African IK on droughts prediction. For example, rainfall is seen as gift from the gods and lack of it as a curse. For example, in reference to the current (2011) drought affecting some parts of Mbeere in Kenya, residents are often heard saying; “we do not know what God wants with us!” Other examples are; (1) Mating of animals was a sign that there was going to be plenty of rains (Roos and Dewald, 2010); (2)Birth of many girl children was sign of good season and more boys a bad season(Mugabe et al, 2010) and (3)Wind blowing to the west would bring rainfall in an hour (Ajibade and Shokemi, 2003).
IK on droughts in Africa is a twin-reality; prediction as well spelling out elaborate coping mechanisms. When drought strikes the Mbeere people, the women specialise in weaving baskets using (mostly) locally available materials and then travel to Central Kenya (Kikuyu land) to exchange them for cereals. Similarly, the women among Bastwanas of South Africa engaged in creative activities such as making clay pots for water storage as well for entrepreneurial purposes (Roos and Dewald, 2010). African communities also have common food preservation practices such as meat drying and stockpiling; these are meant to ensure food availability during shortages.
Though IKFs and SCFs have more differences than similarities, participatory solutions designed around ICTs can be used to make SCFs a compliment to the IKFs. This is because though IKFs are localized and more adapted to the farmers’ context, this knowledge is threatened by phenomena such as climate change, population growth and urbanization. SCFs act as a complement by introducing aspects such global weather parameters. The big question then becomes; how then do we bridge these two diverse sciences of weather forecasting? The authors present one such solution; ITIKI (Information Technology and Indigenous Knowledge with Intelligence); a framework that integrates IKFs and SCFs using mobile phones, wireless sensor networks and intelligent agents. Itiki (pronounced e-ti-ki) is the name given to a kind of a bridge made up of sticks and wires for crossing rivers among the Mbeere people in Eastern part of Kenya.
The recurring and now more frequent and severe droughts experienced in the Sub-Saharan Africa hav... more The recurring and now more frequent and severe droughts experienced in the Sub-Saharan Africa have continuously and systematically weakened the livelihoods of the people living in this Region. Monumental and mostly donor-funded projects have been mounted to counter this but with little success. One of the latest strategies being experimented is a community-based early warning system that seeks to integrate indigenous knowledge with western climate science. This initiative is informed by the realization that weather forecast information provided by the national meteorological departments within the countries in the Region has little utilization amongst the local small-scale farming and pastoralist communities. Though having generated promising results, the integration project faces the challenges of scaling up to more than one community as well as the lack of micro-level weather data needed to validate the integrated weather forecasts. In this paper, we describe how the adoption of mobile phones and wireless sensor networks technology is being used to address these two challenges. Our system makes use of dense wireless sensor networks to collect local weather data while a mobile phones-based application is employed to disseminate localized forecasts. To ensure that the non-mystical aspects of indigenous knowledge are portable across communities, language technologies (part of artificial intelligence) are used in the design of the integrated system.
In 2009, only 3.6% of Kenya’s households owned at least one computer; conversely, 63.2% of househ... more In 2009, only 3.6% of Kenya’s households owned at least one computer; conversely, 63.2% of households owned at least one mobile phone; this is true for many developing countries of Africa. This implies that computing solutions that target mobile phone environments are bound to have greater impact in these countries. However, the inherent constraints of mobile phones present a challenge in implementing viable applications. One solution to this would be to adopt Service Oriented and/or Grid Computing on mobile phones. In this paper, we present results that demonstrate how Service Oriented Computing can enable computation on mobile phones. A java-based questionnaire was implemented as a set of services aimed at overcoming phones’ storage limitation. This was achieved via a middleware that was implemented to manage the services; communication among the services running on different phones was via Bluetooth.
The era of the Internet has brought with it a strong wave that has led to the ever-growing thirst... more The era of the Internet has brought with it a strong wave that has led to the ever-growing thirst for access to any information by anyone, everywhere, anytime and using anything. This has brought with it some form of information-divide that disadvantages the illiterates of this world. For instance, though most farmers in Kenya are illiterate, they often need to access crucial weather information to aid in their decision-making. Among the consequences of this development is the rekindling of research into the Natural Language Interfaces to Databases (NLIDB); an area where research vigor had gone cold. In this paper, we present a system that uses NLIDB to allow non-expert end users in Kenya to access weather information by typing questions in English language. This is an intermediary step in a larger project whose goal is to implement a weather monitoring system for use by farmers in Kenya that allows queries posed (written and/or spoken from a mobile phone) in any local language.
Unlike in other parts of the world, droughts are the leading natural disasters in Africa; they ac... more Unlike in other parts of the world, droughts are the leading natural disasters in Africa; they account for over 90% of effects perpetuated by natural disasters. The problem is compounded by the fact that droughts form a complex web of effects for which the onset, termination and quantification/qualification perplexes researchers to date. Agriculture sector still forms the backbone of most economies in Africa with 70% of output being derived from rain-fed small-scale farming. This sector happens to be the first casualty of droughts and hence the rampant food insecurity problem in most African countries. Accurate, timely and relevant drought predication information enables a community to anticipate and prepare for droughts and hence minimize the negative impacts. Though it may be argued that the science of predicting droughts has come of age especially in the West, the results of such predictions are still alien to African farmers most of whom live in the rural areas where they are still struggling with illiteracy and poor communication infrastructures. However, these farmers are host to indigenous knowledge on not only how to predict droughts but also unique coping strategies. On the other hand, effects of global phenomena such as population growth, climate change, global warming and ICTs revolution cannot be ignored and relying only on indigenous knowledge would endanger any community. Adoption of Wireless Sensor Networks and mobile phones to provide the bridge between scientific and indigenous knowledge weather forecasting methods is one way of ensuring that the content of forecasts and the dissemination formats meet the locals’ needs. A framework for achieving this integration is presented in this paper.
For the last 2 decades, Kenya has consistently contributed the highest number of people affected ... more For the last 2 decades, Kenya has consistently contributed the highest number of people affected by natural disasters in Africa. This is especially so for disasters triggered by climatic variations. The Kenya Meteorological Department has provided regular weather forecasts since the 60s. One of the shortcomings of this Department’s approach is the fact that their forecasts provide conceptual indications of droughts/floods without giving operational indicators. This makes it difficult for key stakeholders to develop solid strategic plans. Innovative use of ICTs can turn around this situation by realigning the forecasts to aid in answering questions such like, how long and how severe the predicted climatic variations will be. Use of cheaper wireless sensors can also help readdress the current poor coverage by weather stations. Based on analysis of 31 years of historical daily precipitation data from three weather stations, we prove that the Effective Drought Index can be used to quantify droughts/floods. We also present an effective web-based system that policy makers can use to monitor droughts/floods on daily basis. In the discussion, we explain how an on-going initiative aimed at enhancing indigenous knowledge with wireless sensor networks and mobile phones will further improve drought monitoring.
Low Internet coverage and lack of electricity in the rural areas of the developing countries of A... more Low Internet coverage and lack of electricity in the rural areas of the developing countries of Africa make use of computer-based solutions a big challenge, yet there is dire need of such applications in these areas. Luckily, most of these countries have reported impressive adoption levels of mobile phones[3], a phenomenon that is now creating a paradigm shift; computing is slowly moving from the traditional PC to the phone. Coincidentally, advancements in the Smartphone technology have produced such powerful gadgets that can ably compete with PCs of the 21st century. Today, for less than US$ 400, one can acquire a Smartphone equipped with; 1000MHz clock speed, 512MiB(ROM+RAM), several data links (CSD, HSCSD, GPRS, EDGE), Wireless local-area network (WLAN) among other features[6]. With this kind of computing power, computer analysts/programmers can now develop both scientific and commercial applications to address numerous challenging facing poor people in the developing countries of Africa.
ABSTRACT The popularity and the high processing power of today's smart phones have presen... more ABSTRACT The popularity and the high processing power of today's smart phones have presented computer scientists with a fertile platform on which to implement grid computing for mobile phones. Such grids will not require much investment since they are designed to make use of `idle' power on already existing phones. This is because most smart phone users only use their phones for a few minutes or a few hours every day and yet, these phones are powered up 24/7. These kinds of grids are most favorable to developing countries where the penetration of mobile phone exceeds other forms of ICTs. Once in place, the grids can then be utilized to run the much-needed applications such e-health, e-education and drought prediction. In this paper, we present MobiGrid, a middleware for mobile phone grid that is part of a larger research project that aims at integrating mobile phones and sensors to come up with a drought predication tool for use in the developing countries. MobiGrid is an API on which distributed applications can be built. Unlike the rest of grid middleware solutions, the uniqueness of our approach lies in the fact that the middleware is for mobile phones environment.
Page 1. Survey on DNS Configurations, Interdependencies, Resilience and Security for *.ke Domains... more Page 1. Survey on DNS Configurations, Interdependencies, Resilience and Security for *.ke Domains James G. Kagwe School of Computing University of Nairobi Nairobi, Kenya kagwejg@gmail.com Muthoni Masinde Hasso ...
The Annual Conference on WWW Applications - 213, Sep 10, 2013
"Internet of Things (IoT) is both an evolutionary and revolutionary paradigm which since its birt... more "Internet of Things (IoT) is both an evolutionary and revolutionary paradigm which since its birth in the late 2008, has received considerable attention especially from researchers. There are a couple of definitions and visions of IoT that can be deduced; the most common vision being the ‘“anywhere, anytime, by anyone and anything”(the “4A vision”) while most common definition is: “IoT is a network of interconnected things/objects that are uniquely addressable”. In the traditional set up, the ‘things’ could be the inherently digital items such as Radio Frequency Identifiers (RFID), mobile phones, motor vehicles and computers; in the ideal IoT paradigm however, the ‘things’ include human beings, plants, domestic/wild animals, basically ‘anything’. Equipped with sensing, on-board processing, communication and storage capabilities, sensors are powerful devices used to autonomously gather and disseminate information on virtually any physical object/process and occurrence of events. The greatest potential of sensors is however realised within wireless sensor networks (WSNs) which are made up of a large number of sensors (commonly referred to as nodes) that cooperatively monitor large environments. It is widely believed that the ‘things’ that really unleashes the power of IoT are the WSNs. Self-configurability, autonomy and easiness of deployment are the salient features of WSNs that make them the main candidates for ‘pervasive computing’ and indeed the 4As vision of IoT paradigm.
Implementation of weather forecasting systems in many Sub-Saharan Africa (SSA) countries is hampered by among other things, inadequate coverage by weather stations. Ideally, when deployed in their hundreds, WSNs-based weather meters can mitigate this by capturing weather parameters at micro-level. However, the reality is different, the cost of sensor boards is still prohibitive; boards cost between 100 to 800 Euros (Bagula et al. 2012). The wireless sensors communication protocols only allow coverage of between 100 and 300M and Global System for Mobile Communications (GSM) in SSA is not reliable enough to support interruption-free communication. Even then, with a functioning WSNs-based drought monitoring system, there is no guarantee that the people (especially the small-scale farmers) that need it most in SSA will utilise the information for an array of reasons that are documented in literature (Masinde 2012). For example, studies reveal that over 80% of farmers in some parts of Ethiopia, Kenya, Zambia and Zimbabwe relied on Indigenous Knowledge Forecasts (IKFs)(Mugabe et al. 2010). This is where Internet of Things (IoT) comes in; instead of creating a homogenous drought forecasting system made up of sensors, a system made up of heterogeneous weather information sources (such as sensors, mobile phones, conventional weather stations, indigenous drought forecasters (rainmakers), mobile phones, smart billboards and so on) would suffice. Though IoT is yet to be realised in the commercial/industrial and business worlds, to address this, a generic service-oriented 5-layered architecture for implementing IoT applications is presented in this paper. This architecture is then used to realise a droughts early warning system. This work therefore affirms that despite the current challenges facing IoT’s real-life implementation, it is possible to implement a simple IoT application to addresses the unique problem of droughts in SSA.
"
Though most factors that trigger droughts cannot be prevented, accurate, relevant and timely fore... more Though most factors that trigger droughts cannot be prevented, accurate, relevant and timely forecasts can be used to mitigate their impacts. Drought forecasts must define the droughts severity, onset, cessation, duration and spatial distribution. Given the high probability of droughts occurrence in Kenya, her heavy reliance on rain-fed agriculture and lack of effective drought mitigation strategies, the Country is highly vulnerable to impacts of droughts. Current drought forecasting approaches used in Kenya are not able to provide short and long term forecasts and they fall short of providing the severity of the drought. In this paper, a combination of Artificial Neural Networks and Effective Drought Index is presented as a potential candidate for addressing these drawbacks. This is demonstrated using forecasting models that were built using weather data for thirty years for four weather stations (representing 3 agro-ecological zones) in Kenya. Experiments varying various input/output combinations were carried out and drought forecasting network models were implemented in MATLAB’s Neural Network Toolbox. The models incorporate forecasted rainfall values in order to mitigate for unexpected extreme climate variations. With accuracies as high as 98%, the solution is a great enhancement to the solutions currently in use in Kenya.
Proceedings of the TU Kaleidoscope conference, Kyoto, Japan, 22-24 April 2013
Mbeere is in Eastern Kenya and it has an average of 550 mm annual rainfall and therefore classifi... more Mbeere is in Eastern Kenya and it has an average of 550 mm annual rainfall and therefore classified under Arid and Semi-Arid Lands. It has fragile ecosystems, unfavorable climate, poor infrastructure and historical marginalization; the perennial natural disasters here are droughts. Of importance to this paper is the fact that despite its vast area of 2,093 km2, there is no single weather station serving the area. The main source of livelihood is rain-fed marginal farming and livestock keeping by small-scale and peasant farmers who rely mostly on the indigenous knowledge of seasons in making cropping decisions. ITIKI; acronym for Information Technology and Indigenous Knowledge with Intelligence is a bridge that integrates indigenous drought forecasting approach into the scientific drought forecasting approach. ITIKI, a framework initiated by the authors of this paper was adopted and adapted from the word itiki which is the name used among the Mbeere people to refer to an indigenous bridge used for decades to go across rivers. ITIKI makes use of mobile phones, wireless sensor networks and artificial intelligence to downscale weather/drought forecasts to individual farmers. ITIKI implementation project in Mbeere commenced in August 2012; this paper describes the implementation roadmap for this project.
Proceedings of the IST-Africa 2013, Nairobi, 29 - 31 May 2013, May 29, 2013
Like most other developing countries of Africa, Kenya’s rain-fed agriculture is the backbone of t... more Like most other developing countries of Africa, Kenya’s rain-fed agriculture is the backbone of the economy. As such, the Country’s economy and weather are so intertwined that a good season means healthy economy and famine, and death otherwise. The status of weather forecasting in Kenya is rather wanting partly because the data used is collected from very sparse network of professional weather stations. Procuring and maintaining these stations is a costly affair for the Country still struggling to meet basic needs for her population. Developments in sensor technology have resulted in affordable and sustainable weatherboards that can operate as mini-weather stations. Though not as good as professional weather stations, these boards can be used to compliment the networks of weather stations, hence improving the accuracy of weather forecasts produced by the Kenya Meteorological Department. We present SenseWeather, a weather monitoring system that we developed using Agriculture Boards from Libelium. In this paper, we describe the design, sensor calibration and deployment of SenseWeather.
Droughts have become chronic in Africa; especially in the Sub-Saharan Africa (Szöllösi-Nagy, 1999... more Droughts have become chronic in Africa; especially in the Sub-Saharan Africa (Szöllösi-Nagy, 1999) where they have resulted in the unending problem of food insecurity. Overall, droughts cause the greatest havoc in Africa; they for example accounted for over 90% of people affected by natural disasters in Africa between 2000 and 2009 (RedCross, 2010). Second in the list were floods (a related disaster), which accounted for a mere 8%. Further, during the same period (2000 to 2009), Africa contributed 46% of all droughts recorded. The complex nature of droughts’ onset-termination has made it acquire the title; “the creeping disaster” (Mishra and Singh, 2010) and unlike other disasters, drought’s effects continue to be felt long after its termination and it spans all aspects of human life. Agriculture still remains one of the key pillars of most economies in Africa. The situation is made worse by the fact that a big chunk (over 70%) comes from vulnerable rain-fed small scale farming operating in fragile environments that are ecologically, geographically and economically marginalized (ISDR, 2008). Farmers in this category would definitely benefit more from drought prediction solutions that are designed with their involvement. These farmers are more interested in customised forecast information that can reliably inform them about the onset, cessation, and intra-seasonal variations in order to reach decisions such as what, when and how to plant/harvest.
The most commonly used form of forecasts used in most countries in Africa is the Seasonal Climate Forecasts (SCFs). Research (Ziervogel and Opere, 2010) has shown that SCFs are too supply-driven and are too ‘course’ to have any relevance at a local community level. The terminologies (e.g. below and normal level) and formats used do not make much sense to most farmers. Furthermore, the mode (websites, radio/television broadcasts and print media) of dissemination does not reach the targeted audience. Consequently, these farmers continue to rely on forecasts that are based on indigenous knowledge (IKFs). For instance, it is in realization of this fact that an initiative (http://www.africa-adapt.net/aa/ProjectOverview.aspx?PID=PUXVdbXh9bM%3D) aimed at integrating SCFs with IKFs was piloted in Kenya. The integration was geared towards maximizing the strengths of the two (SCFs and IKFs) and by extension to improve the adoption of weather forecasts by small-scale farmers. Started in September 2008, the project brought together meteorologists and the Nganyi indigenous knowledge forecasters to build ‘reconciliations’ between SCFs and IKFs. The reconciled forecasts were carried out for 7 seasons between 2007 and 2011 and results disseminated through the locally available (existing) communication channels such as chief barazas and churches. The outcome of the project was rated ‘very good’ by the two parties.
There has been a sharp increase in publications in the area of Indigenous Knowledge (IK) in Africa especially in South Africa where tens of research projects are funded through the National Research Foundation (Loubser, 2005). Despite this encouraging trend, publications in the category of weather/droughts/climate-variation prediction are still rare. For instance, in a recent study (Njiraine et al, 2010) on IK research in Kenya and South Africa, publications directly and indirectly touching on this topic were those under agriculture and environment categories. Unlike other categories such as culture (with 41.2% for Kenya and 31% for South Africa), these (agriculture and environment) categories had minimal representations of 11.5% and 7.5% for agriculture and 12% and 6.9% for environment; the percentages are for Kenya and South Africa respectively. Generally, publications under IK on drought/weather management in Africa ((ISDR, 2008), (Ziervogel and Opere, 2010), (Ajibade and Shokemi, 2003), (Roos and Dewald, 2010), (Steiner, 2008) and (UNEP, 2011)) reveal that communities in Africa used more or less common approaches in predicting drought/weather. They observed changing seasons as well as lunar cycles (shape/position of the moon and patterns of stars). They also observed the natural environment (behavior of animals/birds and looks of some plants) and like the weathermen of today, IK also involved studying the meteorological parameters such as air/temperature intensity, clouds colour/direction and wind direction. Religious beliefs and myths also contributed greatly to African IK on droughts prediction. For example, rainfall is seen as gift from the gods and lack of it as a curse. For example, in reference to the current (2011) drought affecting some parts of Mbeere in Kenya, residents are often heard saying; “we do not know what God wants with us!” Other examples are; (1) Mating of animals was a sign that there was going to be plenty of rains (Roos and Dewald, 2010); (2)Birth of many girl children was sign of good season and more boys a bad season(Mugabe et al, 2010) and (3)Wind blowing to the west would bring rainfall in an hour (Ajibade and Shokemi, 2003).
IK on droughts in Africa is a twin-reality; prediction as well spelling out elaborate coping mechanisms. When drought strikes the Mbeere people, the women specialise in weaving baskets using (mostly) locally available materials and then travel to Central Kenya (Kikuyu land) to exchange them for cereals. Similarly, the women among Bastwanas of South Africa engaged in creative activities such as making clay pots for water storage as well for entrepreneurial purposes (Roos and Dewald, 2010). African communities also have common food preservation practices such as meat drying and stockpiling; these are meant to ensure food availability during shortages.
Though IKFs and SCFs have more differences than similarities, participatory solutions designed around ICTs can be used to make SCFs a compliment to the IKFs. This is because though IKFs are localized and more adapted to the farmers’ context, this knowledge is threatened by phenomena such as climate change, population growth and urbanization. SCFs act as a complement by introducing aspects such global weather parameters. The big question then becomes; how then do we bridge these two diverse sciences of weather forecasting? The authors present one such solution; ITIKI (Information Technology and Indigenous Knowledge with Intelligence); a framework that integrates IKFs and SCFs using mobile phones, wireless sensor networks and intelligent agents. Itiki (pronounced e-ti-ki) is the name given to a kind of a bridge made up of sticks and wires for crossing rivers among the Mbeere people in Eastern part of Kenya.
The recurring and now more frequent and severe droughts experienced in the Sub-Saharan Africa hav... more The recurring and now more frequent and severe droughts experienced in the Sub-Saharan Africa have continuously and systematically weakened the livelihoods of the people living in this Region. Monumental and mostly donor-funded projects have been mounted to counter this but with little success. One of the latest strategies being experimented is a community-based early warning system that seeks to integrate indigenous knowledge with western climate science. This initiative is informed by the realization that weather forecast information provided by the national meteorological departments within the countries in the Region has little utilization amongst the local small-scale farming and pastoralist communities. Though having generated promising results, the integration project faces the challenges of scaling up to more than one community as well as the lack of micro-level weather data needed to validate the integrated weather forecasts. In this paper, we describe how the adoption of mobile phones and wireless sensor networks technology is being used to address these two challenges. Our system makes use of dense wireless sensor networks to collect local weather data while a mobile phones-based application is employed to disseminate localized forecasts. To ensure that the non-mystical aspects of indigenous knowledge are portable across communities, language technologies (part of artificial intelligence) are used in the design of the integrated system.
In 2009, only 3.6% of Kenya’s households owned at least one computer; conversely, 63.2% of househ... more In 2009, only 3.6% of Kenya’s households owned at least one computer; conversely, 63.2% of households owned at least one mobile phone; this is true for many developing countries of Africa. This implies that computing solutions that target mobile phone environments are bound to have greater impact in these countries. However, the inherent constraints of mobile phones present a challenge in implementing viable applications. One solution to this would be to adopt Service Oriented and/or Grid Computing on mobile phones. In this paper, we present results that demonstrate how Service Oriented Computing can enable computation on mobile phones. A java-based questionnaire was implemented as a set of services aimed at overcoming phones’ storage limitation. This was achieved via a middleware that was implemented to manage the services; communication among the services running on different phones was via Bluetooth.
The era of the Internet has brought with it a strong wave that has led to the ever-growing thirst... more The era of the Internet has brought with it a strong wave that has led to the ever-growing thirst for access to any information by anyone, everywhere, anytime and using anything. This has brought with it some form of information-divide that disadvantages the illiterates of this world. For instance, though most farmers in Kenya are illiterate, they often need to access crucial weather information to aid in their decision-making. Among the consequences of this development is the rekindling of research into the Natural Language Interfaces to Databases (NLIDB); an area where research vigor had gone cold. In this paper, we present a system that uses NLIDB to allow non-expert end users in Kenya to access weather information by typing questions in English language. This is an intermediary step in a larger project whose goal is to implement a weather monitoring system for use by farmers in Kenya that allows queries posed (written and/or spoken from a mobile phone) in any local language.
Unlike in other parts of the world, droughts are the leading natural disasters in Africa; they ac... more Unlike in other parts of the world, droughts are the leading natural disasters in Africa; they account for over 90% of effects perpetuated by natural disasters. The problem is compounded by the fact that droughts form a complex web of effects for which the onset, termination and quantification/qualification perplexes researchers to date. Agriculture sector still forms the backbone of most economies in Africa with 70% of output being derived from rain-fed small-scale farming. This sector happens to be the first casualty of droughts and hence the rampant food insecurity problem in most African countries. Accurate, timely and relevant drought predication information enables a community to anticipate and prepare for droughts and hence minimize the negative impacts. Though it may be argued that the science of predicting droughts has come of age especially in the West, the results of such predictions are still alien to African farmers most of whom live in the rural areas where they are still struggling with illiteracy and poor communication infrastructures. However, these farmers are host to indigenous knowledge on not only how to predict droughts but also unique coping strategies. On the other hand, effects of global phenomena such as population growth, climate change, global warming and ICTs revolution cannot be ignored and relying only on indigenous knowledge would endanger any community. Adoption of Wireless Sensor Networks and mobile phones to provide the bridge between scientific and indigenous knowledge weather forecasting methods is one way of ensuring that the content of forecasts and the dissemination formats meet the locals’ needs. A framework for achieving this integration is presented in this paper.
For the last 2 decades, Kenya has consistently contributed the highest number of people affected ... more For the last 2 decades, Kenya has consistently contributed the highest number of people affected by natural disasters in Africa. This is especially so for disasters triggered by climatic variations. The Kenya Meteorological Department has provided regular weather forecasts since the 60s. One of the shortcomings of this Department’s approach is the fact that their forecasts provide conceptual indications of droughts/floods without giving operational indicators. This makes it difficult for key stakeholders to develop solid strategic plans. Innovative use of ICTs can turn around this situation by realigning the forecasts to aid in answering questions such like, how long and how severe the predicted climatic variations will be. Use of cheaper wireless sensors can also help readdress the current poor coverage by weather stations. Based on analysis of 31 years of historical daily precipitation data from three weather stations, we prove that the Effective Drought Index can be used to quantify droughts/floods. We also present an effective web-based system that policy makers can use to monitor droughts/floods on daily basis. In the discussion, we explain how an on-going initiative aimed at enhancing indigenous knowledge with wireless sensor networks and mobile phones will further improve drought monitoring.
Uploads
Books by Muthoni Masinde
Papers by Muthoni Masinde
Implementation of weather forecasting systems in many Sub-Saharan Africa (SSA) countries is hampered by among other things, inadequate coverage by weather stations. Ideally, when deployed in their hundreds, WSNs-based weather meters can mitigate this by capturing weather parameters at micro-level. However, the reality is different, the cost of sensor boards is still prohibitive; boards cost between 100 to 800 Euros (Bagula et al. 2012). The wireless sensors communication protocols only allow coverage of between 100 and 300M and Global System for Mobile Communications (GSM) in SSA is not reliable enough to support interruption-free communication. Even then, with a functioning WSNs-based drought monitoring system, there is no guarantee that the people (especially the small-scale farmers) that need it most in SSA will utilise the information for an array of reasons that are documented in literature (Masinde 2012). For example, studies reveal that over 80% of farmers in some parts of Ethiopia, Kenya, Zambia and Zimbabwe relied on Indigenous Knowledge Forecasts (IKFs)(Mugabe et al. 2010). This is where Internet of Things (IoT) comes in; instead of creating a homogenous drought forecasting system made up of sensors, a system made up of heterogeneous weather information sources (such as sensors, mobile phones, conventional weather stations, indigenous drought forecasters (rainmakers), mobile phones, smart billboards and so on) would suffice. Though IoT is yet to be realised in the commercial/industrial and business worlds, to address this, a generic service-oriented 5-layered architecture for implementing IoT applications is presented in this paper. This architecture is then used to realise a droughts early warning system. This work therefore affirms that despite the current challenges facing IoT’s real-life implementation, it is possible to implement a simple IoT application to addresses the unique problem of droughts in SSA.
"
The most commonly used form of forecasts used in most countries in Africa is the Seasonal Climate Forecasts (SCFs). Research (Ziervogel and Opere, 2010) has shown that SCFs are too supply-driven and are too ‘course’ to have any relevance at a local community level. The terminologies (e.g. below and normal level) and formats used do not make much sense to most farmers. Furthermore, the mode (websites, radio/television broadcasts and print media) of dissemination does not reach the targeted audience. Consequently, these farmers continue to rely on forecasts that are based on indigenous knowledge (IKFs). For instance, it is in realization of this fact that an initiative (http://www.africa-adapt.net/aa/ProjectOverview.aspx?PID=PUXVdbXh9bM%3D) aimed at integrating SCFs with IKFs was piloted in Kenya. The integration was geared towards maximizing the strengths of the two (SCFs and IKFs) and by extension to improve the adoption of weather forecasts by small-scale farmers. Started in September 2008, the project brought together meteorologists and the Nganyi indigenous knowledge forecasters to build ‘reconciliations’ between SCFs and IKFs. The reconciled forecasts were carried out for 7 seasons between 2007 and 2011 and results disseminated through the locally available (existing) communication channels such as chief barazas and churches. The outcome of the project was rated ‘very good’ by the two parties.
There has been a sharp increase in publications in the area of Indigenous Knowledge (IK) in Africa especially in South Africa where tens of research projects are funded through the National Research Foundation (Loubser, 2005). Despite this encouraging trend, publications in the category of weather/droughts/climate-variation prediction are still rare. For instance, in a recent study (Njiraine et al, 2010) on IK research in Kenya and South Africa, publications directly and indirectly touching on this topic were those under agriculture and environment categories. Unlike other categories such as culture (with 41.2% for Kenya and 31% for South Africa), these (agriculture and environment) categories had minimal representations of 11.5% and 7.5% for agriculture and 12% and 6.9% for environment; the percentages are for Kenya and South Africa respectively. Generally, publications under IK on drought/weather management in Africa ((ISDR, 2008), (Ziervogel and Opere, 2010), (Ajibade and Shokemi, 2003), (Roos and Dewald, 2010), (Steiner, 2008) and (UNEP, 2011)) reveal that communities in Africa used more or less common approaches in predicting drought/weather. They observed changing seasons as well as lunar cycles (shape/position of the moon and patterns of stars). They also observed the natural environment (behavior of animals/birds and looks of some plants) and like the weathermen of today, IK also involved studying the meteorological parameters such as air/temperature intensity, clouds colour/direction and wind direction. Religious beliefs and myths also contributed greatly to African IK on droughts prediction. For example, rainfall is seen as gift from the gods and lack of it as a curse. For example, in reference to the current (2011) drought affecting some parts of Mbeere in Kenya, residents are often heard saying; “we do not know what God wants with us!” Other examples are; (1) Mating of animals was a sign that there was going to be plenty of rains (Roos and Dewald, 2010); (2)Birth of many girl children was sign of good season and more boys a bad season(Mugabe et al, 2010) and (3)Wind blowing to the west would bring rainfall in an hour (Ajibade and Shokemi, 2003).
IK on droughts in Africa is a twin-reality; prediction as well spelling out elaborate coping mechanisms. When drought strikes the Mbeere people, the women specialise in weaving baskets using (mostly) locally available materials and then travel to Central Kenya (Kikuyu land) to exchange them for cereals. Similarly, the women among Bastwanas of South Africa engaged in creative activities such as making clay pots for water storage as well for entrepreneurial purposes (Roos and Dewald, 2010). African communities also have common food preservation practices such as meat drying and stockpiling; these are meant to ensure food availability during shortages.
Though IKFs and SCFs have more differences than similarities, participatory solutions designed around ICTs can be used to make SCFs a compliment to the IKFs. This is because though IKFs are localized and more adapted to the farmers’ context, this knowledge is threatened by phenomena such as climate change, population growth and urbanization. SCFs act as a complement by introducing aspects such global weather parameters. The big question then becomes; how then do we bridge these two diverse sciences of weather forecasting? The authors present one such solution; ITIKI (Information Technology and Indigenous Knowledge with Intelligence); a framework that integrates IKFs and SCFs using mobile phones, wireless sensor networks and intelligent agents. Itiki (pronounced e-ti-ki) is the name given to a kind of a bridge made up of sticks and wires for crossing rivers among the Mbeere people in Eastern part of Kenya.
Implementation of weather forecasting systems in many Sub-Saharan Africa (SSA) countries is hampered by among other things, inadequate coverage by weather stations. Ideally, when deployed in their hundreds, WSNs-based weather meters can mitigate this by capturing weather parameters at micro-level. However, the reality is different, the cost of sensor boards is still prohibitive; boards cost between 100 to 800 Euros (Bagula et al. 2012). The wireless sensors communication protocols only allow coverage of between 100 and 300M and Global System for Mobile Communications (GSM) in SSA is not reliable enough to support interruption-free communication. Even then, with a functioning WSNs-based drought monitoring system, there is no guarantee that the people (especially the small-scale farmers) that need it most in SSA will utilise the information for an array of reasons that are documented in literature (Masinde 2012). For example, studies reveal that over 80% of farmers in some parts of Ethiopia, Kenya, Zambia and Zimbabwe relied on Indigenous Knowledge Forecasts (IKFs)(Mugabe et al. 2010). This is where Internet of Things (IoT) comes in; instead of creating a homogenous drought forecasting system made up of sensors, a system made up of heterogeneous weather information sources (such as sensors, mobile phones, conventional weather stations, indigenous drought forecasters (rainmakers), mobile phones, smart billboards and so on) would suffice. Though IoT is yet to be realised in the commercial/industrial and business worlds, to address this, a generic service-oriented 5-layered architecture for implementing IoT applications is presented in this paper. This architecture is then used to realise a droughts early warning system. This work therefore affirms that despite the current challenges facing IoT’s real-life implementation, it is possible to implement a simple IoT application to addresses the unique problem of droughts in SSA.
"
The most commonly used form of forecasts used in most countries in Africa is the Seasonal Climate Forecasts (SCFs). Research (Ziervogel and Opere, 2010) has shown that SCFs are too supply-driven and are too ‘course’ to have any relevance at a local community level. The terminologies (e.g. below and normal level) and formats used do not make much sense to most farmers. Furthermore, the mode (websites, radio/television broadcasts and print media) of dissemination does not reach the targeted audience. Consequently, these farmers continue to rely on forecasts that are based on indigenous knowledge (IKFs). For instance, it is in realization of this fact that an initiative (http://www.africa-adapt.net/aa/ProjectOverview.aspx?PID=PUXVdbXh9bM%3D) aimed at integrating SCFs with IKFs was piloted in Kenya. The integration was geared towards maximizing the strengths of the two (SCFs and IKFs) and by extension to improve the adoption of weather forecasts by small-scale farmers. Started in September 2008, the project brought together meteorologists and the Nganyi indigenous knowledge forecasters to build ‘reconciliations’ between SCFs and IKFs. The reconciled forecasts were carried out for 7 seasons between 2007 and 2011 and results disseminated through the locally available (existing) communication channels such as chief barazas and churches. The outcome of the project was rated ‘very good’ by the two parties.
There has been a sharp increase in publications in the area of Indigenous Knowledge (IK) in Africa especially in South Africa where tens of research projects are funded through the National Research Foundation (Loubser, 2005). Despite this encouraging trend, publications in the category of weather/droughts/climate-variation prediction are still rare. For instance, in a recent study (Njiraine et al, 2010) on IK research in Kenya and South Africa, publications directly and indirectly touching on this topic were those under agriculture and environment categories. Unlike other categories such as culture (with 41.2% for Kenya and 31% for South Africa), these (agriculture and environment) categories had minimal representations of 11.5% and 7.5% for agriculture and 12% and 6.9% for environment; the percentages are for Kenya and South Africa respectively. Generally, publications under IK on drought/weather management in Africa ((ISDR, 2008), (Ziervogel and Opere, 2010), (Ajibade and Shokemi, 2003), (Roos and Dewald, 2010), (Steiner, 2008) and (UNEP, 2011)) reveal that communities in Africa used more or less common approaches in predicting drought/weather. They observed changing seasons as well as lunar cycles (shape/position of the moon and patterns of stars). They also observed the natural environment (behavior of animals/birds and looks of some plants) and like the weathermen of today, IK also involved studying the meteorological parameters such as air/temperature intensity, clouds colour/direction and wind direction. Religious beliefs and myths also contributed greatly to African IK on droughts prediction. For example, rainfall is seen as gift from the gods and lack of it as a curse. For example, in reference to the current (2011) drought affecting some parts of Mbeere in Kenya, residents are often heard saying; “we do not know what God wants with us!” Other examples are; (1) Mating of animals was a sign that there was going to be plenty of rains (Roos and Dewald, 2010); (2)Birth of many girl children was sign of good season and more boys a bad season(Mugabe et al, 2010) and (3)Wind blowing to the west would bring rainfall in an hour (Ajibade and Shokemi, 2003).
IK on droughts in Africa is a twin-reality; prediction as well spelling out elaborate coping mechanisms. When drought strikes the Mbeere people, the women specialise in weaving baskets using (mostly) locally available materials and then travel to Central Kenya (Kikuyu land) to exchange them for cereals. Similarly, the women among Bastwanas of South Africa engaged in creative activities such as making clay pots for water storage as well for entrepreneurial purposes (Roos and Dewald, 2010). African communities also have common food preservation practices such as meat drying and stockpiling; these are meant to ensure food availability during shortages.
Though IKFs and SCFs have more differences than similarities, participatory solutions designed around ICTs can be used to make SCFs a compliment to the IKFs. This is because though IKFs are localized and more adapted to the farmers’ context, this knowledge is threatened by phenomena such as climate change, population growth and urbanization. SCFs act as a complement by introducing aspects such global weather parameters. The big question then becomes; how then do we bridge these two diverse sciences of weather forecasting? The authors present one such solution; ITIKI (Information Technology and Indigenous Knowledge with Intelligence); a framework that integrates IKFs and SCFs using mobile phones, wireless sensor networks and intelligent agents. Itiki (pronounced e-ti-ki) is the name given to a kind of a bridge made up of sticks and wires for crossing rivers among the Mbeere people in Eastern part of Kenya.