| Popis: |
Crop yield is usually affected by impending weather, climate conditions, and human interventions like irrigation. Hence, the prompt detection of regions experiencing water scarcity can aid in implementing effective mitigation strategies. Our study utilized a data-driven approach to compute a Water Demand Index (WDI), which incorporates crucial first-order geophysical variables like ambient temperature, vegetation status, and soil moisture, to identify water-stressed fields in Senegal’s agricultural regions during the millet planting, growing, and harvesting periods. We have also explored various scenarios for enhancing the accuracy of millet yield prediction by incorporating other drought indices, soil characteristics, and a bias correction factor. The novel aspects of this research include the development of regional crop yield predictive models based on sub-seasonal and unaggregated crop information to reflect local variances. To optimize the hyperparameters of machine learning (ML) models, various techniques were utilized. Meanwhile, the performance of these ML models was evaluated using a nested cross-validation approach. The outcomes of the analysis demonstrate that the Random Forest Regressor model exhibits superior predictive performance. The results imply that a holistic approach, encompassing diverse environmental factors and crop growth stages, could result in more precise and dependable millet yield predictions. These results mark a leap forward in crop yield prediction for data-poor regions, paving the way for more accurate and efficient agricultural management. By emphasizing the critical role of detailed, spatio-temporal data, this work substantially enhances model precision, informing targeted strategies to boost yields. This advancement stands to serve producers and consumers alike, fostering sustainable, high-yield agriculture. |
Full Text from ScienceDirect