The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco

In this study, Explainable Artificial Intelligence (XAI) techniques were applied to identify the most important factors influencing crop yield prediction, with a focus on strategies for sustainable agriculture. Using permutation importance and residual plot analysis, the results showed that nitrogen...

Full description

Saved in:
Bibliographic Details
Main Authors: Oumnia Ennaji, Abdellah Hamma, Leonardus Vergütz, Achraf El Allali
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525001832
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145408152502272
author Oumnia Ennaji
Abdellah Hamma
Leonardus Vergütz
Achraf El Allali
author_facet Oumnia Ennaji
Abdellah Hamma
Leonardus Vergütz
Achraf El Allali
author_sort Oumnia Ennaji
collection DOAJ
description In this study, Explainable Artificial Intelligence (XAI) techniques were applied to identify the most important factors influencing crop yield prediction, with a focus on strategies for sustainable agriculture. Using permutation importance and residual plot analysis, the results showed that nitrogen (N) content, Bandera variety and potassium oxide (K2O) are the most important traits influencing yield prediction. Extreme Gradient Boosting (XGB) was used to predict yield using a large Moroccan national cereal dataset spanning 3 seasons. Residual Plots Analysis, Partial Dependent Plots (PDP), Permutation Importance (PI) and SHapley Additive ExPlanations (SHap) were used to select the features that influence yield prediction. The results indicate that optimizing soil nitrogen and potassium oxide levels together with strategic selection of crop varieties can significantly increase productivity. Residual analysis of the eXtreme Gradient Boosting (XGB) model confirmed its high predictive accuracy. This study underlines the value of XAI methods in improving the interpretability of predictive models. The insights gained can contribute to better soil management and informed crop selection, ultimately reducing yield losses under environmental stress. By increasing the resilience of agricultural systems, we aim to contribute to sustainable and data-driven farming practices and, in particular, address some of Morocco's unique agricultural challenges.
format Article
id doaj-art-07b32bacd5c24f11ac5aa4d67433cf1b
institution OA Journals
issn 2772-3755
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-07b32bacd5c24f11ac5aa4d67433cf1b2025-08-20T02:28:07ZengElsevierSmart Agricultural Technology2772-37552025-08-011110095010.1016/j.atech.2025.100950The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in MoroccoOumnia Ennaji0Abdellah Hamma1Leonardus Vergütz2Achraf El Allali3College of Computing, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, Morocco; College of Agriculture and Environmental Sciences, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, Morocco; Corresponding author at: College of Computing, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, Morocco.College of Agriculture and Environmental Sciences, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, MoroccoCollege of Agriculture and Environmental Sciences, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, MoroccoCollege of Computing, Mohammed VI Polytechnic University, Lot 660, Ben Guerir, 43150, Morocco; Principal corresponding author.In this study, Explainable Artificial Intelligence (XAI) techniques were applied to identify the most important factors influencing crop yield prediction, with a focus on strategies for sustainable agriculture. Using permutation importance and residual plot analysis, the results showed that nitrogen (N) content, Bandera variety and potassium oxide (K2O) are the most important traits influencing yield prediction. Extreme Gradient Boosting (XGB) was used to predict yield using a large Moroccan national cereal dataset spanning 3 seasons. Residual Plots Analysis, Partial Dependent Plots (PDP), Permutation Importance (PI) and SHapley Additive ExPlanations (SHap) were used to select the features that influence yield prediction. The results indicate that optimizing soil nitrogen and potassium oxide levels together with strategic selection of crop varieties can significantly increase productivity. Residual analysis of the eXtreme Gradient Boosting (XGB) model confirmed its high predictive accuracy. This study underlines the value of XAI methods in improving the interpretability of predictive models. The insights gained can contribute to better soil management and informed crop selection, ultimately reducing yield losses under environmental stress. By increasing the resilience of agricultural systems, we aim to contribute to sustainable and data-driven farming practices and, in particular, address some of Morocco's unique agricultural challenges.http://www.sciencedirect.com/science/article/pii/S2772375525001832Machine learningYield predictionGrain productionExplainable artificial intelligence
spellingShingle Oumnia Ennaji
Abdellah Hamma
Leonardus Vergütz
Achraf El Allali
The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
Smart Agricultural Technology
Machine learning
Yield prediction
Grain production
Explainable artificial intelligence
title The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
title_full The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
title_fullStr The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
title_full_unstemmed The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
title_short The assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in Morocco
title_sort assessment of soil variables relative importance for cereal yield prediction under rainfed cropping system in morocco
topic Machine learning
Yield prediction
Grain production
Explainable artificial intelligence
url http://www.sciencedirect.com/science/article/pii/S2772375525001832
work_keys_str_mv AT oumniaennaji theassessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT abdellahhamma theassessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT leonardusvergutz theassessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT achrafelallali theassessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT oumniaennaji assessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT abdellahhamma assessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT leonardusvergutz assessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco
AT achrafelallali assessmentofsoilvariablesrelativeimportanceforcerealyieldpredictionunderrainfedcroppingsysteminmorocco