Cereal yield forecasting with satellite drought-based indices, weather data and regional climate indices using machine learning in morocco
Bouras, El Houssaine LU
; Jarlan, Lionel
; Er-Raki, Salah
; Balaghi, Riad
; Amazirh, Abdelhakim
; Richard, Bastien
and Khabba, Saïd
(2021)
In Remote Sensing
13(16).
- Abstract
Accurate seasonal forecasting of cereal yields is an important decision support tool for countries, such as Morocco, that are not self-sufficient in order to predict, as early as possible, importation needs. This study aims to develop an early forecasting model of cereal yields (soft wheat, barley and durum wheat) at the scale of the agricultural province considering the 15 most productive over 2000–2017 (i.e., 15 × 18 = 270 yields values). To this objective, we built on previous works that showed a tight linkage between cereal yields and various datasets including weather data (rainfall and air temperature), regional climate indices (North Atlantic Oscillation in particular), and drought indices derived from satellite observations in... (More)
Accurate seasonal forecasting of cereal yields is an important decision support tool for countries, such as Morocco, that are not self-sufficient in order to predict, as early as possible, importation needs. This study aims to develop an early forecasting model of cereal yields (soft wheat, barley and durum wheat) at the scale of the agricultural province considering the 15 most productive over 2000–2017 (i.e., 15 × 18 = 270 yields values). To this objective, we built on previous works that showed a tight linkage between cereal yields and various datasets including weather data (rainfall and air temperature), regional climate indices (North Atlantic Oscillation in particular), and drought indices derived from satellite observations in different wavelengths. The combination of the latter three data sets is assessed to predict cereal yields using linear (Multiple Linear Regression, MLR) and non-linear (Support Vector Machine, SVM; Random Forest, RF, and eXtreme Gradient Boost, XGBoost) machine learning algorithms. The calibration of the algorithmic parameters of the different approaches are carried out using a 5-fold cross validation technique and a leave-one-out method is implemented for model validation. The statistical metrics of the models are first analyzed as a function of the input datasets that are used, and as a function of the lead times, from 4 months to 2 months before harvest. The results show that combining data from multiple sources outperformed models based on one dataset only. In addition, the satellite drought indices are a major source of information for cereal prediction when the forecasting is carried out close to harvest (2 months before), while weather data and, to a lesser extent, climate indices, are key variables for earlier predictions. The best models can accurately predict yield in January (4 months before harvest) with an R2 = 0.88 and RMSE around 0.22 t. ha−1 . The XGBoost method exhibited the best metrics. Finally, training a specific model separately for each group of provinces, instead of one global model, improved the prediction performance by reducing the RMSE by 10% to 35% depending on the provinces. In conclusion, the results of this study pointed out that combining remote sensing drought indices with climate and weather variables using a machine learning technique is a promising approach for cereal yield forecasting.
(Less)
- author
- Bouras, El Houssaine
LU
; Jarlan, Lionel
; Er-Raki, Salah
; Balaghi, Riad
; Amazirh, Abdelhakim
; Richard, Bastien
and Khabba, Saïd
- publishing date
- 2021-08-02
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Climate indices, Crop yield forecasting, Machine learning, Remote sensing drought indices, Semiarid region, Weather data
- in
- Remote Sensing
- volume
- 13
- issue
- 16
- article number
- 3101
- publisher
- MDPI AG
- external identifiers
-
- scopus:85112308659
- ISSN
- 2072-4292
- DOI
- 10.3390/rs13163101
- language
- English
- LU publication?
- no
- additional info
- Funding Information: This work was carried out within the framework of the Joint International Laboratory TREMA (http://lmi-trema.ma, accessed on 31 July 2021). This work was funded by the ERANETMED03–62 CHAAMS project, the ACCWA project, grant agreement no: 823965 and by SAGESSE PPR/2015/48. E. Bouras was supported by a fellowship from the ARTS program from IRD, France. The H2020 PRIMA ALTOS project, MISTRALS/SICMED2, PHC Toubkal #39064WG/2018 and PRIMA-IDEWA project are also acknowledged for additional funding. Acknowledgments: The authors acknowledge the Economic Services of the Ministry of Agriculture of Morocco for providing the crop production statistics. The authors are also grateful for the valuable and constructive comments from the anonymous reviewers. Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
- id
- 877db101-cbba-4dad-9b48-a7eb9bd338cb
- date added to LUP
- 2023-01-04 09:47:45
- date last changed
- 2023-01-31 13:18:47
@article{877db101-cbba-4dad-9b48-a7eb9bd338cb,
abstract = {{<p>Accurate seasonal forecasting of cereal yields is an important decision support tool for countries, such as Morocco, that are not self-sufficient in order to predict, as early as possible, importation needs. This study aims to develop an early forecasting model of cereal yields (soft wheat, barley and durum wheat) at the scale of the agricultural province considering the 15 most productive over 2000–2017 (i.e., 15 × 18 = 270 yields values). To this objective, we built on previous works that showed a tight linkage between cereal yields and various datasets including weather data (rainfall and air temperature), regional climate indices (North Atlantic Oscillation in particular), and drought indices derived from satellite observations in different wavelengths. The combination of the latter three data sets is assessed to predict cereal yields using linear (Multiple Linear Regression, MLR) and non-linear (Support Vector Machine, SVM; Random Forest, RF, and eXtreme Gradient Boost, XGBoost) machine learning algorithms. The calibration of the algorithmic parameters of the different approaches are carried out using a 5-fold cross validation technique and a leave-one-out method is implemented for model validation. The statistical metrics of the models are first analyzed as a function of the input datasets that are used, and as a function of the lead times, from 4 months to 2 months before harvest. The results show that combining data from multiple sources outperformed models based on one dataset only. In addition, the satellite drought indices are a major source of information for cereal prediction when the forecasting is carried out close to harvest (2 months before), while weather data and, to a lesser extent, climate indices, are key variables for earlier predictions. The best models can accurately predict yield in January (4 months before harvest) with an R<sup>2</sup> = 0.88 and RMSE around 0.22 t. ha<sup>−1</sup> . The XGBoost method exhibited the best metrics. Finally, training a specific model separately for each group of provinces, instead of one global model, improved the prediction performance by reducing the RMSE by 10% to 35% depending on the provinces. In conclusion, the results of this study pointed out that combining remote sensing drought indices with climate and weather variables using a machine learning technique is a promising approach for cereal yield forecasting.</p>}},
author = {{Bouras, El Houssaine and Jarlan, Lionel and Er-Raki, Salah and Balaghi, Riad and Amazirh, Abdelhakim and Richard, Bastien and Khabba, Saïd}},
issn = {{2072-4292}},
keywords = {{Climate indices; Crop yield forecasting; Machine learning; Remote sensing drought indices; Semiarid region; Weather data}},
language = {{eng}},
month = {{08}},
number = {{16}},
publisher = {{MDPI AG}},
series = {{Remote Sensing}},
title = {{Cereal yield forecasting with satellite drought-based indices, weather data and regional climate indices using machine learning in morocco}},
url = {{http://dx.doi.org/10.3390/rs13163101}},
doi = {{10.3390/rs13163101}},
volume = {{13}},
year = {{2021}},
}