Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Multi-Model Ensemble Approach for Soybean

Crop Yield Estimation (Kharif-2023) in
Latur District at Macroscale level
Ashutosh Pawar Upasana Singh
Head, GIS and RS, Semantic Technologies and Sr. GIS and RS Executive, Semantic Technologies and
Agritech Services Pvt. Ltd., Pune. Agritech Services Pvt. Ltd., Pune.

Priyanka Shamraj Bhargav Sonawane

Agrometeorologist, Semantic Technologies and Jr. RS Executive Semantic Technologies and
Agritech Services Pvt. Ltd., Pune. Agritech Services Pvt. Ltd., Pune.

Abstract:- Crop area estimation is a critical aspect of Unpredictable rainfall, rising temperatures, and extreme
agricultural monitoring and management, providing weather events like hailstorms and strong winds threaten crop
essential information for decision-making in the growth and yields. Farmers shift to drought-resistant crops,
agricultural sector. Study was carried out at Semantic rely heavily on irrigation, face soil degradation, and
Technologies and Agritech services Pvt. Ltd., GIS and experience economic vulnerability due to unstable
Remote sensing team, Pune during Kharif-2023. All production.
methodology given by YESTECH manual under Pradhan
Mantri Fasal Bima Yojana (PFMBY) was followed. Latur In the contemporary agricultural landscape, the accurate
district facing more weather-based yield losses during last estimation of crop yield has emerged as a critical aspect
few of years. In this case study we tried to estimate yield influencing various sectors including insurance, economy,
of soybean crop for agriculture-based stake holders, government policies, and ultimately, the welfare of farmers.
insurance companies, Government polices at Revenue Traditional methods of crop yield estimation are often marred
circle level (RC). Multimodal approach is beneficial over by limitations in accuracy and efficiency. However, the
single model yield estimation approach as it takes integration of advanced technologies, such as sophisticated
ensemble yield for perfect forecasting of crop yield. software, remote sensing, GIS (Geographic Information
Accuracy was in the range as given in YESTECH manual System), and cutting-edge artificial intelligence (AI) and
at RC level. Thus, overall results show that use of such machine learning (ML) techniques, has revolutionized the
model for yield estimation is one of the best approach to precision and reliability of crop yield estimation.
take the decisions for insurance based stake holders in
rainfed regions where more negative consequences on  Importance of Accurate Crop Yield Estimation:
soybean productivity under different climate change
scenario was observed.  Insurance Sector: Accurate crop yield estimates play a
pivotal role in the insurance sector, enabling precise risk
Keywords:- Remote Sensing, GIS, NPP, Machine Learning, assessment and facilitating the development of tailored
DSSAT-4.8, Soybean, Latur, Yield Simulation, Revenue insurance products.
Circle, Soybean productivity.  Economic Implications: Crop yield estimates are
fundamental to economic forecasting, impacting
I. INTRODUCTION commodity markets, trade agreements, and pricing
mechanisms.
Agriculture is the backbone of global economies,  Government Policies: Governments rely on accurate crop
providing sustenance and livelihoods for billions of people. yield estimates to formulate effective agricultural policies.
The ability to accurately predict crop yield is paramount for This includes allocation of subsidies, distribution of
effective resource management, risk mitigation, and informed resources, and planning for strategic interventions during
decision-making. Traditional methods, reliant on historical periods of adverse weather conditions or pest outbreaks.
data and manual observations, often fall short in addressing  Public Welfare and Food Security: Accurate crop yield
the dynamic nature of modern agricultural challenges. The estimates are integral to ensuring food security and public
integration of advanced technologies has ushered in a new era welfare.
in agriculture, enabling a more nuanced and precise  Farmers' Wellbeing: For farmers, precise crop yield
understanding of crop dynamics. Software applications, estimates translate into enhanced planning and risk
remote sensing, GIS, and AI/ML algorithms work management. Access to reliable information empowers
synergistically to process vast datasets, analyse patterns, and farmers to make informed decisions regarding crop
predict crop yields with unprecedented accuracy.

IJISRT24MAR1981 www.ijisrt.com 2475

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

selection, resource allocation, and market participation, II. MATERIAL AND METHODS
thereby improving overall farm productivity and
livelihoods. A. Study Area
Study was carried out at Semantic Technologies and
The adoption of advanced methods for crop yield Agritech Services Pvt. Ltd., Pune during kharif season 2023
estimation is a transformative step towards building for particular assignment. For this study, all revenue circles
agricultural resilience in the face of evolving challenges. The (RC) in the districts of Latur of Maharashtra state were used
synergy between software applications, remote sensing, and as experimental sites. Field level data like ground truth, Crop
GIS technologies empowers stakeholders across sectors to cutting experiments were carried out.
make informed decisions, fostering a sustainable and
prosperous future for agriculture. By recognizing the B. Geography and Climate for Latur District:
multifaceted implications of accurate crop yield estimation, Latur districts cover 7,157 sq km of area. Annual rainfall
societies can work collaboratively to strengthen the averages 520 mm, with Kharif season receiving 350-390 mm.
foundations of global food security, economic stability, and Kharif temperatures range from 33-37°C maximum and 22-
the welfare of farming communities. 25°C minimum, with average relative humidity of 70-80%
located at latitudes 17°52′N to 18°50′N, 75°16′E to 76°42′E.
This report delves into the significance of employing Elevations range from 400-800 m. Soil and Drainage can be
advanced methods for estimating crop yield and highlights described as , Vertisols dominate the region, posing drainage
their implications across diverse domains. challenges due to flat topography and leading to waterlogging
during heavy rainfall. Situated in Boundary of Karnataka-
Maharashtra border, the district is surrounded by Osmanabad
in the South, Beed in the West, Parbhani and Nanded in the
North and Bidar district of Karnataka in the East. Soybean,
cotton, jowar, bajra, tur, and sugarcane is one of the major
crops which is taken in this district.

Fig 1: Study Area

IJISRT24MAR1981 www.ijisrt.com 2476

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

C. Methodology:  Semi Physical NPP- Net Primary Productivity

All methodology was followed by the procedure given  AI and Machine learning
by yield estimation system based on technology (yes-tech)  Crop simulation model-DSSAT-4.8
under Pradhan Mantri Fasal Bima Yojana (PMFBY).  Ensemble Model

Methodology used is multimodal approach for  Semi Physical Net Primary Productivity (NPP):
estimation of crop yield was given below. RC wise yield in
Tonnes/hector of soybean crop during kharif season 2023 was  Data and Materials Used:
estimated by all following methods. The data and materials used in this study are as follows:

Table 1: Data used for NPP Generation in Semi Physical Model

Data Satellite/Ground Resolution Source
Daily insolation/PAR INSAT-3D 4km resampled to 1km MOSDAC
10 days composite fAPAR ver. 2 PROBA V and SPOT-VGT 1km Copernicus Land
Service
8 Days Composite Surface Terra-MODIS 1km MODIS Time Series Tool
Reflectance
Paddy Mask Sentinel 1 5m USGS Explorer
Temperature Gridded data from 1km Interpolated NASA Power
NASA Power website
Light-use Efficiency Literature
Harvest Index Ground CCE

 Fraction of Absorbed PAR (FAPAR):

The FAPAR data is from Copernicus Land Service, Wstess = (𝟏−𝑳𝑺𝑾𝑰)/ (𝟏+𝑳𝑺𝑾𝑰𝒎𝒂𝒙)
source link is (https: //land. copernicus. eu/global/index.
html). the 10 - day composite product with 1 km data is used. The LSWImax value has been taken from the spatial
The range of FAPAR lies between 0 and 1. The physical maximum of particular crop mask of the entire district.
values are retrieved from the Digital Number (DN).
 Temperature Stress:
 Photosynthetically Absorbed Radiation (PAR): Temperature Stress (Tstress): The daily average
PAR is calculated from daily insolation data. The daily temperature data is downloaded from NASA Power website,
insolation data is converted to 8 - day composite (sum) for the source link is (https: //power. larc. nasa. gov/data - access -
whole period. 50% insolation is considered as PAR. This viewer. html). It is a gridded data with a resolution of 1°0 *
daily insolation data is collected from MOSDAC from 1°0 latitude and longitude.
INSAT - 3D satellite, source link (www.mosdac. gov. in) for
the crop season from 2018 to 2022.

PAR= 8 - day composite * 0.5.

 Water Stress (Wstress):

The Wstress is calculated from Land Surface Water
Index (LSWI). The MODIS time series tool (MODIStsp) Where,
used to download and process the MODIS 8 day composite  Tmin = Minimum temperature required for the
(MOD09A1) source link is (https: //lpdaac. usgs. photosynthesis (°C).
gov/products/mod09a1v006), and LSWI is calculated for the  Tmax =Maximum temperature required for the
entire period with the formula . photosynthesis (°C).
 Topt = Optimal temperature required for the
LSWI = (ƿ𝑵𝑰𝑹−ƿ𝑺𝑾𝑰𝑹)/ (ƿ𝑵𝑰𝑹+ƿ𝑺𝑾𝑰𝑹) photosynthesis (°C);
 T = Daily mean temperature (°C).
LSWI value range from - 1 to 1, and higher positive
values indicate the vegetation and soil water stress. Further,
the Wstress is calculated from 8 days LSWI output –

Table 2: Data used for Soybean Crop for Semi-Physical Approach.

Sr.No. Particulars Values Source Sr.No. Particulars Values Source
1 T maximum 35°C (Nimje, P. 4 LUE 1.78 (Chavan et al., 2018)
2 T minimum 10°C M. 2022) 5 Harvest Index 0.45 Periodic CCE data.
3 T optimum 26°C

IJISRT24MAR1981 www.ijisrt.com 2477

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

On the off chance that air temperature falls beneath  Calculation of NPP and Grain Yield:
Tmin, which is quite a rare chance than Tscalar value will To compute the final Net Primary Productivity NPP and
automatically become 0. its Grain Yield, the formula and equation is used as follows.
The NPP sum has been multiplied with Harvest Index (0.45)
 Light Use Efficiency (ℇ): to estimate per pixel yield.
The light use efficiency LUE is used for soybean crop
was 1.78 for the study. NPP = PAR * FAPAR * ℇ * Tstress * Wstress (Logic of
Monteith Equation 1972).
 Crop Mask
The crop mask was derived utilizing Sentinel-1 Same methodology is followed by Upasana Singh et.al.
synthetic aperture radar (SAR) data obtained from the (2023) and also showing same results for all data used to run
European Space Agency (ESA) Copernicus Hub. Employing the model.
the R programming language, we employed the Random
Forest algorithm for the generation of the crop mask,  Crop Simulation Model-DSSAT
implementing hyperparameter tuning techniques and Crop simulation model is a mathematical equation or the
contingency matrix analysis. This methodology was set of equations, which represents the behavior of system. We
systematically applied across our specified crops within the used CROPGRO – for Soybean crop. It is consisting of various
targeted area of interest. subroutines viz., Water balance subroutine, Phenology
subroutine, Nitrogen subroutine, and Growth and
In terms of accuracy assessment, our results yielded a Development subroutine described below.
robust accuracy range of 90% to 95% across all cultivated
crops and within various districts. This signifies a high level  Data Input to Model
of precision in delineating and classifying the specified crops Material and method and all file process was carried out
within the delineated geographical regions. The meticulous by the procedure followed by Hoogenboom, G., et.al (2019)
incorporation of Random Forest algorithm, hyperparameter and (2024) Jones, J.W., (2003) and the minimum data
tuning, and contingency matrix analysis has facilitated the requirements for operation, calibration and validation of the
generation of a reliable and accurate crop mask, providing Crop models are described below.
valuable insights for agricultural monitoring and
management within the designated study area.

Table 3: Showing List of Input Required by Crop Simulation Model

Sr.No. Input variables Acronym Source
1. SITE DATA
Latitude LAT NASA power
Longitude LONG NASA power
Elevation ELEV NASA power
2. DAILY WEATHER DATA
Maximum temperature TEMPMAX NASA power
Minimum temperature TEMPMIN NASA power
Solar radiation SOLARAD NASA power
Rainfall RAIN NASA power
3. SOIL CHARACTERISTICS
Soil texture SLTX
Soil local classification SLDESC
Soil depth SLDP
Colour, moist SCOM
Albedo (fraction) SALB
Photosynthesis factor (0 to 1 scale) SLPE
pH in buffer determination method SMPX DSSAT website
Potassium determination method SMKE Where Global gridded-
Horizon-wise soil profile dataset at 10-
Lower limit drained LL(L) km resolution was
Upper limit drained DUL(L) Developed for DSSAT-
4.8
Upper limit drained SAT(L)
Software crop simulation
Saturated hydraulic conductivity SWCN(L)
models.
Bulk density moist BD(L)
Organic carbon OC(L)
Clay (<0.002 mm) ` CLAY(L)
Silt (0.05 to 0.002 mm) SILT(L)

IJISRT24MAR1981 www.ijisrt.com 2478

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Coarse fraction (>2 mm) STONES(L)

Total nitrogen TOTN(L)
pH in buffer PHKCL(L)
Cation exchange capacity CEC(L)
Root growth factor 0 to 1 SHF(L)
4 MANAGEMENT DATA
Sowing date YRPLT Krishi-Dainandini
Plant population at seedling PLNATS Published by in Vasantrao
Planting method (TP/direct seeded) PLME Naik Marathwada Krishi
Row spacing ROWSPS Vidypeeth, Parbhani,
Row direction (degree from north) AZIR
Seed rate SDWTRL
Sowing depth SDEPTH
Irrigation dates IDLAPL
Irrigation amount AMT(J)
Method of irrigation IRRCOD
Fertilizer application dates FDAY(J)
Fertilizer amount N ANFER
Fertilizer type IFTYPE
Fertilizer application method FERCOD
Fertilizer incorporation depth DFERT
Tillage date TDATE
Tillage implements TIMPL

 Input files planting material, transplant age, plants per hill, dates of
The files are organized into input, output and simulation beginning etc.
experiment performance data file. The experiment
performance files are needed only when simulated results are  Crop Cultivars Directory File
to be compared with data recorded in a particular experiment. For Soybean CRGRO048 contained the list of different
In some cases, they could be used as input files to reset some cultivars with their genetic coefficients. The modified genetic
variable during the course of a simulation run. The input files coefficients viz., CSDVAR, PPSEN, EMG-FLW, FLW-FSD,
are further divided into those dealing with the experiment, FSD-PHM, WTPSD, SDPDVR, SDFDUR, PODDUR,
weather and soil and the characteristics of different THRESH, SDPRO and SDLIP is used. Variety selected was
genotypes. Similarly output files are also further divided into JS-335 which is mostly used in this area.
those dealing with the overview, summary, growth, water,
carbon and nitrogen balance. The genetic coefficients are the most important
parameters which represents the genetic characteristics of the
 Soil properties directory file: The file SOIL.SOL contained cultivar and on which the crop phenology, biomass
the list of different soils with their physical and chemical production partitioning and yield potential of the crop
properties. depends. However, the actual performance is controlled by
 Soil profile initial condition file: The soil profile initial the external factors also.
condition file contained the initial values of soil water, soil
reaction and soil nitrogen data pertaining to this situation  Running the crop model: Once, all the desired files were
was entered. created carefully the model was run for all the crops
 Irrigation management file: The Irrigation management cultivars. Each run of model created output files.
file has the provision of date and amount per fixed
irrigation (mm) applied depth (cm) of management.  Machine Learning:
Irrigation data pertaining to this situation was entered. Methodology and processing of model is described
 Fertilizer management file: The fertilizer management file below in details.
contained the date, form and amount of nitrogen
application. Accordingly, information on fertilizer  Data Collection and Ground Truthing:
application was entered in the file.
 Treatment management file: The treatment management  Collect remote sensing data (optical and radar imagery)
file contained the description of each treatment under for the study area, covering the growing season of the
separate title and serial numbers. The file also contained crops.
dates of planting and emergence, plant population at  Ground truth data collection using field surveys using
seeding and at emergence, planting method, planting CropTech App ( prepared by compony) for accurate
distribution, row spacing, row direction, planting depth, calibration and validation.

IJISRT24MAR1981 www.ijisrt.com 2479

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

 Crop Mask Extraction:  Crop Cutting Experiments:

 Pre-process the remote sensing data to correct for  Use of Crop Cutting Experiment (CCE) for Crop with
atmospheric interference and geometric distortions. smart sampling methods to efficiently estimate crop
 Apply image enhancement techniques to improve the parameters for crop.
visual quality of the images.
 Employ supervised or unsupervised classification  Training and Testing Models (Machine Learning):
algorithms to extract crop masks for Soybean fields.
 Divide the dataset into training and testing sets, ensuring
 Generation of Spectral Indices and use of RADAR no overlap between the two.
Backscatter:  Evaluate the model's performance on the testing dataset
using evaluation metrics like accuracy, F1-score, and
 Calculate vegetation indices (e.g., NDVI, NDRE, mean squared error (RMSE).
GNDVI) from the optical remote sensing data to assess
crop health and Vigor.  Model Validation and Final Result:
 Utilize backscatter data from radar imagery to analyse
surface roughness and other relevant crop information  Validate the trained model using independent ground truth
(VV, VH). data collected during the growing season for Soybean.
 Assess the model's accuracy and generalization ability to
ensure reliable yield estimation.
 Obtain the final crop yield estimation results for Soybean
in the study area.

Fig 2: Methodology used in Machine learning Approach

 Ensemble Models  Data Collection and Preprocessing:

This methodology aims to combine the predictive power
of both Machine Learning (ML) models and Crop Simulation  Gather data from both ML, Semi-Physical Approach and
Models (CSM) to provide an enhanced and more accurate CSM approaches as outlined in the above methods.
estimation of crop yields. Here is a structured approach:  Consolidate all input data: weather data, soil properties,
crop management practices, spectral indices, RADAR
backscatter, and ground truth data.
 Ensure data alignment in terms of temporal and spatial
granularity.

IJISRT24MAR1981 www.ijisrt.com 2480

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

 Individual Model Generation:  Stacking: Use a meta-model that takes predictions from
individual models as inputs and predicts the final yield.
 Machine Learning Approach:  Voting: Each model votes for a final yield prediction, and
the most frequent prediction is considered.
 Utilize various algorithms like Linear regression, Random
Forest, Extra Trees, k-earest neighbours, and neural  Model Validation
networks.
 Train these models on the dataset ensuring proper  Split the dataset into training, validation, and test sets to
validation and calibration. avoid overfitting and ensure generalizability.
 Use metrics like Root Mean Squared Error (RMSE), and
 Crop Simulation Approach R-squared (R2) for evaluation.
 Assess performance using the test dataset and ground
 Use well-calibrated crop simulation models such as truth data.
DSSAT.
 Simulate the growth and yield of crops using these models  Quality Control
based on provided input data.
 Calculate the normalized RMSE between the observed
 Semi-physical Models: and ensemble model's estimated yield.
A semi-physical model in remote sensing and GIS is a  Ensure RMSE does not exceed acceptable thresholds,
type of model that combines physical principles with refining the model if necessary.
remotely sensed data to estimate or predict biophysical
parameters, such as crop yield, biomass. These models are  Validation
often used to monitor and manage natural resources, as well The accuracy of our model was evaluated based on crop
as to assess the impacts of climate change and other cutting experiment data (CCE data) of PMFBY (Pradhan
environmental stressors. Mantri Fasal Bima Yojana) for the crop season kharif-2023.

 Ensemble Techniques Application: III. RESULTS AND DISCUSSION

 Model Averaging: Calculate the simple mean of Following were the results and conclusion for different
predictions from ML, semi- physical model and CSM methods/models used for estimation of yield of soyabean crop
models. in Latur districts of Maharashtra, Revenue-Circle wise.
 Weighted Averaging: Assign weights based on individual
model performance and calculate the weighted average of
predictions.

A. Semi Physical Approach-NPP:

Fig 3: FAPAR for Latur during Kharif 2023

IJISRT24MAR1981 www.ijisrt.com 2481

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Fig 4: PAR for Latur during Kharif 2023

Fig 5: Tstress for Latur during Kharif 2023

IJISRT24MAR1981 www.ijisrt.com 2482

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Fig. 6: Waterstress for Latur during Kharif 2023

Fig. 7: Soybean Crop Mask of Latur during

IJISRT24MAR1981 www.ijisrt.com 2483

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Fig. 8: Soybean Yield of Latur during Kharif 2023 kharif 2023

 Ahamadpur, Andhori, and Kingaon demonstrated  Overall, most regions achieved yields above 2 tonnes per
relatively higher actual yields, surpassing 2 tonnes per hectare, indicating satisfactory performance for soybean
hectare. cultivation in 2023.
 Hadolati, Belkund, Bhada, Killari, and Shirur Tajband had  Regional variations in climate and agricultural techniques
comparatively lower actual yields, falling below 2 tonnes likely influenced the observed differences in soybean
per hectare. yields. Same results were reported by Xiao, X., et.al
 Semi-Physical (NPP) Yield also showed variation, with (2006) and Yao, Y., et.al (2021)
some areas like Ujani, Chakur, and Latur displaying lower
performance. B. Crop Simulation Model DSSAT-4.8
 Notable outliers include Halgara, which had exceptionally
high actual yields, and Nalgir, which had a notably high  The highest yielding RCs are Halgara and Wadhavana
Semi-Physical Yield. (Bk), both with an average yield of 2.89 tonnes per
 The dataset suggests a need for closer examination of hectare.
factors influencing yield discrepancies between regions,  The lowest yielding RCs are Nalgir and Tandulja, with
such as soil quality and agricultural practices. average yields of 0.77 tonnes per hectare and 1.18 tonnes
per hectare, respectively.

IJISRT24MAR1981 www.ijisrt.com 2484

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Fig 9: Soybean Yield in T/ha by DSSAT for Latur during Kharif 2023

 There is a significant variation in yield between different Bhosale, A. D., et.al (2015) and Deshmukh, S. D.,
RCs, with the highest yielding RCs producing more than et.al (2013) also elaborated same results for soybean.
four times the yield of the lowest yielding RCs.
 There is a significant variation in yield between different C. Machine Learning
RCs, with some RCs having double the yield of others.
 The results suggest the potential benefits of using DSSAT  CCE yield and different indices under study showing
for predicting soybean crop yields, although specific accuracy 82 % in Machine learning model. By the method
environmental factors and RC conditions may influence (SVR) Support Vector Regression accuracy is showing
the accuracy of the predictions. Jadhav, S. D et.al (2018), highest value.

IJISRT24MAR1981 www.ijisrt.com 2485

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Fig 10: Soybean Yield in T/ha by ML for Latur during kharif 2023

 Ahamadpur, Andhori, and Kingaon exhibited relatively  Optimization of ML models can enhance predictive
stable yields around 2 tonnes per hectare in both actual accuracy and contribute to better-informed agricultural
and ML projections. practices.
 Shirur Tajband, Chakur, and Nalegaon showed lower  The results indicate the potential of ML to improve yield
yields, indicating potential challenges in those regions. predictions and optimize crop management strategies.
 Halgara stood out with remarkably high actual yield but
substantially lower ML yield, suggesting potential
discrepancies in the ML model for that area.

IJISRT24MAR1981 www.ijisrt.com 2486

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

D. Ensemble Model:

Fig 11: Soybean Yield in T/ha by Ensemble Model for Latur during Kharif 2023

Table 4: Statistical approach give weightage during kharif 2023 as following to different models.
Model Used DSSAT Yield Semi-Physical Yield Machine Learning Yield
Weightages in % 36.72 33.03 30.25

 The Ensemble Yield represents a combination of all above  The summary reveals the potential of ensemble
three predictive models or methods to estimate soybean techniques in predicting soybean yields, though
crop yield. adjustments may be needed to enhance accuracy in
 Regions like Tandulja, Hisamabad, and Sakol exhibited regions with high % Error.
significant negative percent Error, suggesting  Understanding and minimizing % Error can facilitate
considerable discrepancies between actual and predicted better decision-making for farmers and policymakers,
yields. optimizing agricultural practices and resource allocation.
 Conversely, regions like Walandi and Shelgaon showed  Continuous refinement and validation of predictive
positive percent Error, indicating slight overestimations in models can contribute to more reliable yield forecasts,
yield predictions. supporting sustainable soybean production in Latur
 Ensemble Yield tended to align closely with Actual yield district. Same results were given by Md Didarul Islam
in some regions, such as Dewrjan and Borol, where the et.al (2023), Liujun Xiao et.al. (2022) and Ayan Das a
percent Error was minimal or zero. et.al (2023) in both Machine learning and ensemble
approach.

IJISRT24MAR1981 www.ijisrt.com 2487

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Table 5: Estimated Yield of Soybean Crop in Tones/Hectors with Different Models and
Percent Error with Ensemble Model for Year 2023
District Tehsil RC Field CCE DSSAT Semi- Machine Ensemble RMSE %
Yield Physical Learning Yield Error
Yield Yield
Latur Ahmadpur Ahamadpur 1.69 2.31 2.22 2.10 2.22 -31
Latur Ahmadpur Andhori 2.14 2.28 2.43 2.06 2.27 -7
Latur Ahmadpur Hadolati 1.77 2.30 1.64 2.10 2.01 -14
Latur Ahmadpur Khandali 1.58 2.66 2.01 2.08 2.28 -44
Latur Ahmadpur Kingaon 2.08 2.33 2.73 2.06 2.40 -15
Latur Ahmadpur Shirur tajband 1.35 2.05 2.01 1.33 1.84 -37
Latur Ausa Ausa 2.12 2.23 2.29 2.15 2.23 -5
Latur Ausa Belkund 1.84 2.18 1.68 2.07 1.97 -7
Latur Ausa Bhada 2.19 2.11 1.87 2.15 2.04 7
Latur Ausa Killari 2.00 2.27 1.73 2.06 2.02 -1
Latur Ausa Kinithot 2.28 2.42 2.14 2.12 2.24 2
Latur Ausa Lamjana 2.18 2.53 1.84 2.12 2.18 0
Latur Ausa Matola 2.08 2.09 1.72 2.08 1.96 6
Latur Ausa Ujani 2.71 2.51 1.70 2.08 2.11 22
Latur Chakur Ashta 1.82 2.51 2.42 2.08 2.36 -30
Latur Chakur Chakur 1.30 2.21 2.68 1.29 2.13 -63
Latur Chakur Nalegaon 1.34 2.60 1.99 1.23 2.02 -51
Latur Chakur Shelgaon 2.26 2.32 2.48 2.12 2.32 -3
Latur Chakur Wadwal (Na) 1.28 2.26 1.97 1.24 1.89 -47
Latur Chakur Zari Bk 1.35 2.74 2.41 1.28 2.24 -66
Latur Deoni Borol 2.04 2.06 2.01 2.15 2.07 -2
Latur Deoni Deoni 1.41 2.33 2.23 1.25 2.01 -42
Latur Deoni Walandi 2.58 2.54 1.98 1.23 1.99 23
Latur Jalkot Ghonasi 2.06 2.19 1.94 2.15 2.09 -1
Latur Jalkot Jalkot 2.37 2.22 2.05 2.11 2.13 10
Latur Latur Babhalgaon 1.57 2.05 1.77 2.06 1.95 -24
Latur Latur Chincholi (Bk) 2.26 2.10 2.10 2.14 2.11 7
Latur Latur Gategaon 1.93 2.26 2.03 2.13 2.15 -11
Latur Latur Harangul (Bk) 1.98 2.10 1.89 2.08 2.02 -2
Latur Latur Kanheri 2.01 2.32 1.70 2.11 2.05 -2
Latur Latur Kasarkheda 1.97 2.57 2.23 2.07 2.32 -18
Latur Latur Latur 2.14 2.14 1.68 2.09 1.97 8
Latur Latur Murud (Bk) 2.20 2.53 1.88 2.10 2.19 1
Latur Latur Tandulja 1.18 2.33 2.36 2.15 2.29 -94
Latur Nilanga Ambulga (Bk) 2.47 2.48 2.47 2.12 2.38 4
Latur Nilanga Aurad (Sha) 2.06 2.06 2.05 2.09 2.07 0
Latur Nilanga Bhutmugli 1.99 2.11 1.87 2.08 2.02 -1
Latur Nilanga Halgara 2.89 3.87 1.91 1.32 2.50 14
Latur Nilanga Kasar Balkunda 2.12 2.59 1.65 2.13 2.13 -1
Latur Nilanga Kasar Shirashi 2.28 2.65 1.92 2.07 2.24 2
Latur Nilanga Madansuri 2.02 2.29 1.75 2.06 2.04 -1
Latur Nilanga Nilanga 2.02 2.23 1.82 2.12 2.05 -2
Latur Nilanga Nitur 2.53 2.61 2.46 2.14 2.43 4
Latur Nilanga Panchincholi 2.39 2.53 2.25 2.14 2.33 3
Latur Renapur Karepur 1.23 2.26 2.66 1.30 2.15 -74
Latur Renapur Palsi 1.39 2.25 2.00 1.93 2.08 -49
Latur Renapur Pangaon 2.18 2.53 2.20 2.09 2.29 -5
Latur Renapur Poharegaon 2.30 2.55 2.06 2.18 2.28 1
Latur Renapur Renapur 1.39 2.65 2.11 1.31 2.11 -52
Latur Shirur-Anantpal Hisamabad 1.09 2.45 2.15 1.29 2.04 -86
Latur Shirur-Anantpal Sakol 1.32 2.66 2.52 1.27 2.24 -70
Latur Shirur-Anantpal Shirur Anantpal 1.53 2.06 2.18 1.29 1.90 -24
Latur Udgir Dewrjan 2.16 2.38 1.93 2.15 2.16 0
Latur Udgir Her 2.39 2.30 2.48 2.15 2.32 3
Latur Udgir Mogha 2.12 2.22 2.03 2.17 2.14 -1
Latur Udgir Nagalgaon 2.40 2.59 2.20 2.15 2.34 2
Latur Udgir Nalgir 1.57 0.77 2.37 2.15 1.70 -8
Latur Udgir Tondar 2.21 2.08 2.33 2.18 2.20 0
Latur Udgir Udgir 2.36 2.19 2.53 2.12 2.29 3

IJISRT24MAR1981 www.ijisrt.com 2488

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

Latur Udgir Wadhavana(Bk) 2.62 2.56 2.68 2.12 2.49 5

Latur district Average values = 1.968 2.342 2.107 1.929 2.149 -14.41

Table 6: Average Percent Error of all Approaches Estimated Yield of Soybean Crop for Year 2023.
Methods Field CCE DSSAT Yield Semi-Physical Yield Machine Learning Yield Ensemble Yield
Yield (T/h) 1.97 2.34 2.11 1.93 2.15
RMSE % Error -19 -7 2 -9

In Table 4, the yield estimated by various methods is REFERENCES

presented, including the percentage error of yield by the
ensemble model with field CCE, which is provided in the last [1]. Ayan Das, Mukesh Kumar, Amit Kushwaha, Rucha
column. Out of 62 points only 14 points were showing more Dave, Kailash Kamaji Dakhore, Karshan Chaudhari,
than 30% error. As per mentioned in deliverables in & Bimal Kumar Bhattacharya. (2023). Machine
YESTECH manual given by Pradhan Mantri Fasal Bima learning model ensemble for predicting sugarcane
Yojana, the error (nRMSE) between the observed and yield through synergy of optical and SAR remote
modeled yield should not be more than ±30% for district sensing. Remote Sensing Applications: Society and
level. While, in table no. 5 average yields and % errors for Environment, Volume 30, April 2023, 100962.
whole Latur district are mentioned. All values of % error https://doi.org/10.1016/j.rsase.2023.100962
presenting error was less than ±30%. Which indicates that the [2]. Bhosale, A. D., Waskar, D. P., & Shinde, P. B. (2015).
process adopted for RC wise Soybean yield estimation is Performance of DSSAT model for simulating soybean
acceptable for Latur district for all the models. yield under rainfed condition in Vertisols of central
Maharashtra. International Journal of Agriculture,
IV. CONCLUSION Environment and Biotechnology, 8(3), 604-610.
[3]. Chavan, K.K., Khobragade, A.M., Kadam, Y.E. and
"The comparative evaluation of NPP, DSSAT, and Mane, R.B. (2018) Study the heat unit requirement of
Machine Learning models for predicting soybean crop yields soybean (Glycine max) varieties under varied weather
in Latur, Maharashtra for kharif 2023 has provided a nuanced condition at Parbhani. Journal of Pharmacognosy and
understanding of their individual strengths and limitations. Phytochemistry. 7(3): 526-530.
Each model demonstrated distinct capabilities in capturing [4]. Deshmukh, S. D., Waskar, D. P., & Shinde, P. B.
the complexities of crop growth dynamics, with Machine (2013). Application of DSSAT model for soybean
Learning showcasing its adaptability and predictive accuracy. yield prediction in Vertisols of western Maharashtra.
International Journal of Current Microbiology and
The ensemble model, combining NPP, DSSAT, and Applied Sciences, 2(8), 555-562.
Machine Learning, offered a holistic perspective by [5]. Hoogenboom, G., C.H. Porter, K.J. Boote, V. Shelia,
leveraging the strengths of individual models. This P.W. Wilkens, U. Singh, J.W. White, S. Asseng, J.I.
integration allowed for a more robust and reliable prediction Lizaso, L.P. Moreno, W. Pavan, R. Ogoshi, L.A. Hunt,
of crop yields, providing a comprehensive overview of the G.Y. Tsuji, and J.W. Jones. (2019). The DSSAT crop
crop performance over the study period. modeling ecosystem. In: p.173-216 [K.J. Boote,
editor] Advances in Crop Modeling for a Sustainable
Comparisons between the ensemble model results and Agriculture. Burleigh Dodds Science Publishing,
field data revealed a promising alignment, emphasizing the Cambridge, United Kingdom.
potential of ensemble modelling in enhancing the accuracy of https://dx.doi.org/10.19103/AS.2019.0061.10.
yield predictions. The combined approach contributes to [6]. Hoogenboom, G., C.H. Porter, V. Shelia, K.J. Boote,
minimizing uncertainties associated with individual models U. Singh, W. Pavan, F.A.A. Oliveira, L.P. Moreno-
and provides a more reliable basis for decision-making in Cadena, T.B. Ferreira, J.W. White, J.I. Lizaso, D.N.L.
agriculture. Pequeno, B.A. Kimball, P.D. Alderman, K.R. Thorp,
S.V. Cuadra, M.S. Vianna, F.J. Villalobos, W.D.
In conclusion, the integration of NPP, DSSAT, and Batchelor, S. Asseng, M.R. Jones, A. Hopf, H.B. Dias,
Machine Learning models into an ensemble framework L.A. Hunt, and J.W. Jones. (2024). Decision Support
presents a promising avenue for advancing crop yield System for Agrotechnology Transfer (DSSAT)
prediction methodologies. This study serves as a foundation Version 4.8.2 (www.DSSAT.net). DSSAT
for further research and refinement, with the ultimate goal of Foundation, Gainesville, Florida, USA.
providing farmers and policymakers with accurate and [7]. Jadhav, S. D., Waskar, D. P., & Shinde, P. B. (2018).
actionable insights for sustainable agricultural practices in Evaluation of DSSAT model for soybean yield
Latur District of Maharashtra State." prediction under different sowing dates and irrigation
levels in Vidarbha region of Maharashtra. Journal of
AgriSearch, 6(4), 37-42.

IJISRT24MAR1981 www.ijisrt.com 2489

Volume 9, Issue 3, March – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24MAR1981

[8]. Jones, J.W., G. Hoogenboom, C.H. Porter, K.J. Boote,

W.D. Batchelor, L.A. Hunt, P.W. Wilkens, U. Singh,
A.J. Gijsman, and J.T. Ritchie. (2003). The DSSAT
cropping system model. European Journal of
Agronomy, 18, 235-265.
https://doi.org/10.1016/S1161-0301(02)00107-7
[9]. Liujun Xiao, Guocheng Wang, Hangxin Zhou, Xiao
Jin, & Zhongkui Luo. (2022). Coupling agricultural
system models with machine learning to facilitate
regional predictions of management practices and
crop production. Environ. Res. Lett., 17(2022),
114027. https://doi.org/10.1088/1748-9326/ac9c71
[10]. Md Didarul Islam, Liping Di, Faisal Mueen Qamer,
Sravan Shrestha, Liying Guo, Li Lin, Timothy J.
Mayer, & Aparna R. Phalke. (2023). Rapid Rice Yield
Estimation Using Integrated Remote Sensing and
Meteorological Data and Machine Learning. Remote
Sensing, 15(9), 2374. Remote Sensing | Free Full-Text
| Rapid Rice Yield Estimation Using Integrated
Remote Sensing and Meteorological Data and
Machine Learning (mdpi.com)
[11]. Monteith, J. L. (1982). Solar radiation and
productivity in tropical ecosystems. Journal of
Applied Ecology, 19(3), 657-666.
[12]. Nimje, P. M. (2022) Soybean Production technology,
National Skill Development Corporation AISECT,
Agriculture Skill Council of India 2022.
(https://www.nsdcindia.org/scmp/assets/image/19135
97640-
20_SoybeanProductionTechnology_preview.pdf)
[13]. Upasana Singh, Gargi Gaydhane and Ashutosh Pawar
(2023) A Semi - Physical Approach using Remote
Sensing based Net Primary Productivity (NPP),
Spatial, Spectral & Temporal Paddy Yield Model
Development for the State of Assam. International
Journal of Science and Research (IJSR). 12 (8),1175-
1785.
[14]. VNMKV Diary 2023 Krishi Dainandini 2023
published by Vasantrao Naik Marathwada Krishi
Vidyapeeth, Parbhani during 2023.
[15]. Xiao, X., Boles, S., Frolking, S., Li, C., Babu, J. Y.,
Salas, W., & Moore III, B. (2006). Mapping paddy
rice agriculture in South and Southeast Asia using
multi-temporal MODIS images. Remote Sensing of
Environment, 100(1), 95-113.
[16]. Yao, Y., Li, Z., Tian, F., & Tao, F. (2021). Remote
Sensing-Based Estimation of Maize Yield Using a
Semi-Physical Approach: A Case Study in the North
China Plain. Frontiers in Plant Science, 12, 662.

IJISRT24MAR1981 www.ijisrt.com 2490