Integrating APSIM model with machine learning to predict wheat yield spatial distribution

Traditional simulation models are often point based; thus, more research is needed to emphasize spatial simulation, providing decision-makers with fast recommendations. Combining machine learning algorithms with spatial process-based models could be considered an appropriate solution. We created a s...

Descripción completa

Detalles Bibliográficos
Autores principales: Kheir, A.M.S., Mkuhlani, S., Mugo, J.W., Elnashar, A., Nangia, V., Devare, Medha, Govind, A.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Wiley 2023
Materias:
Acceso en línea:https://hdl.handle.net/10568/134729
_version_ 1855528904726413312
author Kheir, A.M.S.
Mkuhlani, S.
Mugo, J.W.
Elnashar, A.
Nangia, V.
Devare, Medha
Govind, A.
author_browse Devare, Medha
Elnashar, A.
Govind, A.
Kheir, A.M.S.
Mkuhlani, S.
Mugo, J.W.
Nangia, V.
author_facet Kheir, A.M.S.
Mkuhlani, S.
Mugo, J.W.
Elnashar, A.
Nangia, V.
Devare, Medha
Govind, A.
author_sort Kheir, A.M.S.
collection Repository of Agricultural Research Outputs (CGSpace)
description Traditional simulation models are often point based; thus, more research is needed to emphasize spatial simulation, providing decision-makers with fast recommendations. Combining machine learning algorithms with spatial process-based models could be considered an appropriate solution. We created a spatial model in R (APSIMx_R) to generate fine-resolution data from coarse-resolution data, which is typically available at the regional level. The APSIM crop model outputs were then deployed to train and test the artificial neural network, creating a hybrid modeling approach for robust spatial simulations. The APSIMx_R package facilitates preparing the required model inputs, executes the prediction, processes, and analyzes the APSIM crop model outputs. This note demonstrates the use of a new approach for creating reproducible crop modeling workflows with the spatial APSIM next-generation model and machine learning algorithms. The tool was deployed for spatial and temporal simulation of potential wheat yield under different nitrogen rates and various wheat cultivars. The spatial APSIMx_R was validated by comparing the simulated yield at 100 kg N ha−1 to the analogues' actual yield at the same grid points, which showed good agreement (d = 0.89) between the spatially predicted and actual yield. The hybrid approach increased such precision, resulting in higher agreement (d = 0.95) with actual yield. When the interaction between cultivars and nitrogen levels was considered, it was found that the novel cultivar Sakha95 is nitrogen voracious, exhibiting a larger drop in yield (65%) under minimal nitrogen treatment (0 kg N ha−1) relative to the potential yield.
format Journal Article
id CGSpace134729
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Wiley
publisherStr Wiley
record_format dspace
spelling CGSpace1347292025-12-02T10:59:51Z Integrating APSIM model with machine learning to predict wheat yield spatial distribution Kheir, A.M.S. Mkuhlani, S. Mugo, J.W. Elnashar, A. Nangia, V. Devare, Medha Govind, A. machine learning wheat yields varieties models Traditional simulation models are often point based; thus, more research is needed to emphasize spatial simulation, providing decision-makers with fast recommendations. Combining machine learning algorithms with spatial process-based models could be considered an appropriate solution. We created a spatial model in R (APSIMx_R) to generate fine-resolution data from coarse-resolution data, which is typically available at the regional level. The APSIM crop model outputs were then deployed to train and test the artificial neural network, creating a hybrid modeling approach for robust spatial simulations. The APSIMx_R package facilitates preparing the required model inputs, executes the prediction, processes, and analyzes the APSIM crop model outputs. This note demonstrates the use of a new approach for creating reproducible crop modeling workflows with the spatial APSIM next-generation model and machine learning algorithms. The tool was deployed for spatial and temporal simulation of potential wheat yield under different nitrogen rates and various wheat cultivars. The spatial APSIMx_R was validated by comparing the simulated yield at 100 kg N ha−1 to the analogues' actual yield at the same grid points, which showed good agreement (d = 0.89) between the spatially predicted and actual yield. The hybrid approach increased such precision, resulting in higher agreement (d = 0.95) with actual yield. When the interaction between cultivars and nitrogen levels was considered, it was found that the novel cultivar Sakha95 is nitrogen voracious, exhibiting a larger drop in yield (65%) under minimal nitrogen treatment (0 kg N ha−1) relative to the potential yield. 2023-11 2023-11-27T12:36:34Z 2023-11-27T12:36:34Z Journal Article https://hdl.handle.net/10568/134729 en Open Access application/pdf Wiley Kheir, A.M.S., Mkuhlani, S., Mugo, J.W., Elnashar, A., Nangia, V., Devare, M. & Govind, A. (2023). Integrating APSIM model with machine learning to predict wheat yield spatial distribution. Agronomy Journal, 1-9.
spellingShingle machine learning
wheat
yields
varieties
models
Kheir, A.M.S.
Mkuhlani, S.
Mugo, J.W.
Elnashar, A.
Nangia, V.
Devare, Medha
Govind, A.
Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title_full Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title_fullStr Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title_full_unstemmed Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title_short Integrating APSIM model with machine learning to predict wheat yield spatial distribution
title_sort integrating apsim model with machine learning to predict wheat yield spatial distribution
topic machine learning
wheat
yields
varieties
models
url https://hdl.handle.net/10568/134729
work_keys_str_mv AT kheirams integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT mkuhlanis integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT mugojw integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT elnashara integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT nangiav integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT devaremedha integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution
AT govinda integratingapsimmodelwithmachinelearningtopredictwheatyieldspatialdistribution