Cereal Yield Forecasting with Satellite Drought-Based Indices, Weather Data and Regional Climate Indices Using Machine Learning in Morocco

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 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.

Choosing multiple linear regressions for weather-based crop yield prediction with ABSOLUT v1.2 applied to the districts of Germany

“…The question remains, to what extent information absorbed in the model setup process and henceforth contained in model structures makes overconfidence in predictions from new input data a common issue, not only in weather-based crop yield modelling. In recent years, machine learning algorithms gained popularity in crop modelling with seemingly better results than multiple regression modelling (Cai et al 2019 ; Cao et al 2021 ; Leng and Hall 2020 ; Zhang et al 2020 ; Bouras et al 2021 ). However, practically all of these studies have in common that an initial selection of predictor variables was made using all available data (and often simple tools like Pearson correlations) before the advanced methods were applied.…”

Indicator-to-impact links to help improve agricultural drought preparedness in Thailand

“…AI is very effective in finding patterns and connections within large volumes of multi-source spatio-temporal information, while Bayesian models are well suited for modelling complex spatio-temporal variations and capturing uncertainties. Shen et al (2019) used Deep Learning technique (Artificial Neural Network) to build a drought monitoring model in China, whereas Bouras et al (2021) developed a crop yield forecasting tool based on eXtreme Gradient Boost (XGBoost) in Morocco. Salakpi et al (2022) on the other hand, used a dynamic hierarchical Bayesian approach for forecasting vegetation condition in Kenya.…”

Combining Remote Sensing and Meteorological Data for Improved Rice Plant Potassium Content Estimation

“…ML algorithms do not require certain assumptions (e.g., normal distribution) as opposed to statistical approaches [26]. Therefore, ML is increasingly used for monitoring and mapping agricultural systems [26][27][28][29][30][31][32][33][34][35][36][37][38]. This study will employ two types of machine learning methods (i.e., PLSR and random forest (RF)) for rice plant potassium content estimates.…”