Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data,...

Descripción completa

Detalles Bibliográficos
Autores principales: Kheir, Ahmed M.S., Govind, Ajit, Nangia, Vinay, Devkota Wasti, Mina Kumari, Elnashar, Abdelrazek, Omar, Mohie, Feike, Til
Formato: Journal Article
Lenguaje:Inglés
Publicado: IOP Publishing 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/172410
_version_ 1855514105556762624
author Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
Devkota Wasti, Mina Kumari
Elnashar, Abdelrazek
Omar, Mohie
Feike, Til
author_browse Devkota Wasti, Mina Kumari
Elnashar, Abdelrazek
Feike, Til
Govind, Ajit
Kheir, Ahmed M.S.
Nangia, Vinay
Omar, Mohie
author_facet Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
Devkota Wasti, Mina Kumari
Elnashar, Abdelrazek
Omar, Mohie
Feike, Til
author_sort Kheir, Ahmed M.S.
collection Repository of Agricultural Research Outputs (CGSpace)
description Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data, particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine learning workflow, including automatic training and optimization of multiple models within a userspecified time frame, but it has less attention so far. Here, we combined extensive field survey yield across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to predict field-level wheat yield using 22 Ml models in AutoML. The models showed robust accuracies for yield predictions, recording Willmott degree of agreement, (d>0.80) with higher accuracy when super learner (stacked ensemble) was used (R2=0.51, d=0.82). The trained AutoML was deployed to predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation with actual yield (R2=0.7). This is very important since it is considered a low-cost tool and could be used to explore early yield predictions. Since climate change has negative impacts on agricultural production and food security with some uncertainties, AutoML was deployed to predict wheat yield under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6). These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050). The stacked ensemble model displayed declines in yield of 21% and5%under SSP5-8.5 and SSP2-4.5 respectively during mid-century, with higher uncertainty under the highest emission scenario (SSP5- 8.5). The developed approach could be used as a rapid, accurate and low-cost method to predict yield for stakeholder farms all over the world where ground data is scarce.
format Journal Article
id CGSpace172410
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher IOP Publishing
publisherStr IOP Publishing
record_format dspace
spelling CGSpace1724102026-01-17T02:00:46Z Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset Kheir, Ahmed M.S. Govind, Ajit Nangia, Vinay Devkota Wasti, Mina Kumari Elnashar, Abdelrazek Omar, Mohie Feike, Til climate change wheat remote sensing machine learning yield prediction wheat Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data, particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine learning workflow, including automatic training and optimization of multiple models within a userspecified time frame, but it has less attention so far. Here, we combined extensive field survey yield across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to predict field-level wheat yield using 22 Ml models in AutoML. The models showed robust accuracies for yield predictions, recording Willmott degree of agreement, (d>0.80) with higher accuracy when super learner (stacked ensemble) was used (R2=0.51, d=0.82). The trained AutoML was deployed to predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation with actual yield (R2=0.7). This is very important since it is considered a low-cost tool and could be used to explore early yield predictions. Since climate change has negative impacts on agricultural production and food security with some uncertainties, AutoML was deployed to predict wheat yield under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6). These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050). The stacked ensemble model displayed declines in yield of 21% and5%under SSP5-8.5 and SSP2-4.5 respectively during mid-century, with higher uncertainty under the highest emission scenario (SSP5- 8.5). The developed approach could be used as a rapid, accurate and low-cost method to predict yield for stakeholder farms all over the world where ground data is scarce. 2024-04-25 2025-01-29T15:14:43Z 2025-01-29T15:14:43Z Journal Article https://hdl.handle.net/10568/172410 en Open Access application/pdf IOP Publishing Ahmed M. S. Kheir, Ajit Govind, Vinay Nangia, Mina Kumari Devkota Wasti, Abdelrazek Elnashar, Mohie Omar, Til Feike. (25/4/2024). Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset. Environmental Research Communications, 6 (4).
spellingShingle climate change
wheat
remote sensing
machine learning
yield prediction
wheat
Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
Devkota Wasti, Mina Kumari
Elnashar, Abdelrazek
Omar, Mohie
Feike, Til
Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title_full Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title_fullStr Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title_full_unstemmed Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title_short Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset
title_sort developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing soil and weather dataset
topic climate change
wheat
remote sensing
machine learning
yield prediction
wheat
url https://hdl.handle.net/10568/172410
work_keys_str_mv AT kheirahmedms developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT govindajit developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT nangiavinay developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT devkotawastiminakumari developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT elnasharabdelrazek developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT omarmohie developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset
AT feiketil developingautomatedmachinelearningapproachforfastandrobustcropyieldpredictionusingafusionofremotesensingsoilandweatherdataset