Di Yang

A forest patterns map over a large extent at high spatial resolution is a heavily computation task but is
critical to most regions. There are two major difficulties in generating the classification maps at regional
scale: large training points sets and expensive computation cost in classifier modelling. As one of the
most well-known Volunteered Geographic Information (VGI) initiatives, OpenstreetMap contributes not
only on road network distributions, but the potential of justify land cover and land use. Google Earth
Engine is a platform designed for cloud-based mapping with a strong computing power. In this study,
we proposed a new approach to generating forest cover map and quantifying road-caused forest fragmentations
by using OpenstreetMap in conjunction with remote sensing dataset stored in Google Earth
Engine. Additionally, the landscape metrics produced after incorporating OpenStreetMap (OSM) with
the forest spatial pattern layers from our output indicated significant levels of forest fragmentation in
Yucatan peninsula.

Management practices are one of the most important factors affecting forest structure and function. Landowners in southern United States manage forests using appropriately sized areas, to meet management objectives that include economic return, sustainability, and esthetic enjoyment. Road networks spatially designate the socio-environmental elements for the forests, which represented and aggregated as forest management units. Road networks are widely used for managing forests by setting logging roads and firebreaks. We propose that common types of forest management are practiced in road-delineated units that can be determined by remote sensing satellite imagery coupled with crowd-sourced road network datasets. Satellite sensors do not always capture road-caused canopy openings, so it is difficult to delineate ecologically relevant units based only on satellite data. By integrating citizen-based road networks with the National Land Cover Database, we mapped road-delineated management...

Water is crucial for ecosystem health and socioeconomic development, but water scarcity is becoming a global concern. Management of transboundary watersheds is inherently challenging and has the potential to lead to conflict over the allocation of water resources. The metacoupling framework, which explores the relationships between coupled human and natural systems that are nested within multiple different scales, has been proposed to inform more holistic management of transboundary watersheds. This paper provides the first attempt to apply a metacoupling framework to a transboundary watershed for an improved integrated understanding of this complex system at multiple spatial scales. It does so with the transnational Limpopo River watershed in Southern Africa, which covers 1.3% of the continent and supports the livelihoods of 18.8 million people living in Botswana, Mozambique, South Africa, and Zimbabwe. Sub-Saharan Africa is experiencing a growing gap between water availability and...

Forests in the United States are managed by multiple public and private entities making harmonization of available data and subsequent mapping of management challenging. We mapped four important types of forest management, production, ecological, passive, and preservation, at 250-meter spatial resolution in the Southeastern (SEUS) and Pacific Northwest (PNW) USA. Both ecologically and socio-economically dynamic regions, the SEUS and PNW forests represent, respectively, 22.0% and 10.4% of forests in the coterminous US. We built a random forest classifier using seasonal time-series analysis of 16 years of MODIS 16-day composite Enhanced Vegetation Index, and ancillary data containing forest ownership, roads, US Forest Service wilderness and forestry areas, proportion conifer and proportion riparian. The map accuracies for SEUS are 89% (10-fold cross-validation) and 67% (external validation) and PNW are 91% and 70% respectively with the same validation. The now publicly available fores...

Hurricane Harvey (2017) caused widespread flash flooding by extremely heavy rainfall and resulted in tremendous damage, including 82 fatalities and huge economic loss in the Houston, Texas area. To reduce hazards, loss, and to improve urban resilience, it is important to understand the factors that influence the occurrence of flooding events. People rely on natural resources and different land uses to reduce the severity of flood impacts and mitigate the risk. In this study, we focused the impacts of land use on Hurricane-Harvey-induced flooding inside and outside the Houston city center. With the recent trend that more citizen scientists serve in delivering information about natural disaster response, local residents in Houston areas participated in delineating the flooded areas in Hurricane Harvey. The flooding information used here generated a published map with citizen-contributed flooding data. A regional model framework with spatial autocovariates was employed to understand th...

A land-use map at the regional scale is a heavy computation task yet is critical to most landowners, researchers, and decision-makers, enabling them to make informed decisions for varying objectives. There are two major difficulties in generating land classification maps at the regional scale: the necessity of large data-sets of training points and the expensive computation cost in terms of both money and time. Volunteered Geographic Information opens a new era in mapping and visualizing the physical world by providing an open-access database valuable georeferenced information collected by volunteer citizens. As one of the most well-known VGI initiatives, OpenStreetMap (OSM), contributes not only to road network distribution information but also to the potential for using these data to justify and delineate land patterns. Whereas, most large-scale mapping approaches-including regional and national scales-confuse "land cover" and "land-use", or build up the land-use database based on modeled land cover data-sets, in this study, we clearly distinguished and differentiated land-use from land cover. By focusing on our prime objective of mapping land-use and management practices, a robust regional land-use mapping approach was developed by integrating OSM data with the earth observation remote sensing imagery. Our novel approach incorporates a vital temporal component to large-scale land-use mapping while effectively eliminating the typically burdensome computation and time/money demands of such work. Furthermore, our novel approach in regional scale land-use mapping produced robust results in our study area: the overall internal accuracy of the classifier was 95.2% and the external accuracy of the classifier was measured at 74.8%.

Remote sensing has been widely used in vegetation-dynamics monitoring. Many studies have used data acquired by multispectral sensors, such as the Landsat TM sensor, due to their high spatial resolution (30 m). However, during the growing season, the temporal resolution (16 day) cannot capture rapid changes of vegetation. Meanwhile, coarse-spectral-resolution sensors, such as Moderate Resolution Imaging Spectroradiometer (MODIS), have high-frequency temporal information that can catch the details of landscape changes. In this research, we proposed a data-fusion approach to merge the MODIS and Landsat TM data to create a dataset of vegetation dynamics with both a high spatial resolution and a fine temporal resolution. The Comanche and Faith Ranches, located in west Texas, were chosen for this study. The MODIS product was used as a regionally consistent reference dataset to correct the Landsat imagery. Based on this new dataset, NDVI time-series curves from 2004 to 2011 were calculated with the MODIS 13 Vegetation Dataset. One random sample of red-band images was tested and compared with MODIS data. A high correlation coefficient 0.907 and RMSE 0.0245 was found. OPEN ACCESS 2

In this article, we propose a novel difference image (DI) creation method for unsupervised change detection in multi-temporal multi-spectral remote-sensing images based on deep learning theory. First, we apply a deep belief network to learn local and high-level features from the local neighbour of a given pixel in an unsuper-vised manner. Second, a back propagation algorithm is improved to build a DI based on selected training samples, which can highlight the difference on changed regions and suppress the false changes in unchanged regions. Finally, we get the change trajectory map using simple clustering analysis. The proposed scheme is tested on three remote-sensing data sets. Qualitative and quantitative evaluations show its superior performance compared to the traditional pixel-level and texture-level-based approaches. ARTICLE HISTORY