Predicting crop yields in Senegal using machine learning methods

Sarr, Alioune Badara; Sultan, Benjamin

doi:10.1002/joc.7947

Cited by 17 publications

(6 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This uncertainty range is also reported in the Senegal climate change country profile by McSweeney et al (2008), which indicates decreasing mean annual and wet season rainfall, but with a range of change within -41 to +48% by the 2090s. The decreasing trend in annual precipitation with reductions of 10-20% by the end of the century is also reported in the analysis of Sarr and Sultan (2022). Given these uncertain climate projections, yield changes in West Africa also show a large dispersion from -50% to +90%, with a median negative impact of -18% predicted for the Sudano-Sahelian countries (Roudier et al, 2011).…”

Section: Introductionmentioning

confidence: 57%

Modelling the impacts of water harvesting and climate change on rainfed maize yields in Senegal

Castelli

Setti

Villani

et al. 2022

Preprint

View full text Add to dashboard Cite

The agricultural sector of Senegal is prone to drought and climate change impacts. Despite this, the country counts less than 5% of irrigated lands, suggesting that its national agriculture is still strictly dependent on the rainy season. Moreover, rainfall is characterized by the presence of great variability, both on interannual and interdecadal timescales. In this framework, a research gap is represented by the lack of analyses on how much the current agricultural practices can be resilient, and on what water management strategies can be effective against climate change.Using FAO&#8217;s AquaCrop crop-growth model, made up of a set of four sub-model components (climate, crop, soil, and management) to simulate a crop cycle, we simulated plausible climate change scenarios at different fertility levels, testing the efficiency of tied ridges water harvesting for the maize crop in the Fatick region, Senegal. Non-conservative parameters were adjusted with crop data collected within the project "Rain, Forest and People" of the International Rainwater Harvesting Alliance (IRHA, https://www.irha-h2o.org/en/projects/la-pluie-la-foret-et-les-hommes) while calibration and validation were performed with regional yield data.Considering the current climatic scenario and soil fertility, tied ridges did not significantly impact the maize yields. Rainfall amount was enough for maize production and to avoid high water stresses along the cropping season. Under climate change scenarios, high reductions in yield were registered up to 70% in optimally fertilized soil and 50% in conditions of fertility stress. &#160;Tied ridges only slightly increased yields up to 3.8% when a high reduction of rainfall occurred. When also considering the occurrence of dry spells in addition to climate change, maximum yield reductions do not exceed the values found without dry spells. However, in such context, tied ridges water harvesting performed better against climate change, especially under full fertilization management.Our results highlighted how the current maize production in the Fatick region of Senegal is sustainable in the current climate scenario, while it could be potentially impacted by climate change in the near future. In a pessimistic climate change scenario with dry spells occurring in the rainy season, in-situ water harvesting has the potentiality to avoid excessive crop losses.

show abstract

Section: Introductionmentioning

confidence: 57%

Modelling the impacts of water harvesting and climate change on rainfed maize yields in Senegal

Castelli

Setti

Villani

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A.B. Sarr et al [7] investigate crop yield prediction methods specifically for Senegal. They proposed a study in which they used three machine learning models which are SVM, Random Forest and Neural Network and one multiple linear regression that is Least Absolute Shrinkage and Selection Operator (LASSO) to predict the yield of essential food staple crops in Senegal.…”

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning-Based Crop Yield Prediction in South India: Performance Analysis of Various Models

Nikhil,

Pandiyan,

Raja

et al. 2024

Computers

View full text Add to dashboard Cite

Agriculture is one of the most important activities that produces crop and food that is crucial for the sustenance of a human being. In the present day, agricultural products and crops are not only used for local demand, but globalization has allowed us to export produce to other countries and import from other countries. India is an agricultural nation and depends a lot on its agricultural activities. Prediction of crop production and yield is a necessary activity that allows farmers to estimate storage, optimize resources, increase efficiency and decrease costs. However, farmers usually predict crops based on the region, soil, weather conditions and the crop itself based on experience and estimates which may not be very accurate especially with the constantly changing and unpredictable climactic conditions of the present day. To solve this problem, we aim to predict the production and yield of various crops such as rice, sorghum, cotton, sugarcane and rabi using Machine Learning (ML) models. We train these models with the weather, soil and crop data to predict future crop production and yields of these crops. We have compiled a dataset of attributes that impact crop production and yield from specific states in India and performed a comprehensive study of the performance of various ML Regression Models in predicting crop production and yield. The results indicated that the Extra Trees Regressor achieved the highest performance among the models examined. It attained a R-Squared score of 0.9615 and showed lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) of 21.06 and 33.99. Following closely behind are the Random Forest Regressor and LGBM Regressor, achieving R-Squared scores of 0.9437 and 0.9398 respectively. Moreover, additional analysis revealed that tree-based models, showing a R-Squared score of 0.9353, demonstrate better performance compared to linear and neighbors-based models, which achieved R-Squared scores of 0.8568 and 0.9002 respectively.

show abstract

“…Geospatial technology has good potential for sustainable agricultural development, environmental assessment, assessing crop suitability, monitoring cropland changes, etc. [7][8][9][10][11]. Numerous studies have focused on monitoring land use and land cover (LULC) using a variety of satellite imagery resolutions and techniques, spanning from local to global scales [12,13].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Crop Yield Estimation through Geospatial Technology: A Comparative Analysis of a Semi-Physical Model, Crop Simulation, and Machine Learning Algorithms

Gumma,

Nukala,

Panjala

et al. 2024

AgriEngineering

View full text Add to dashboard Cite

This study underscores the critical importance of accurate crop yield information for national food security and export considerations, with a specific focus on wheat yield estimation at the Gram Panchayat (GP) level in Bareilly district, Uttar Pradesh, using technologies such as machine learning algorithms (ML), the Decision Support System for Agrotechnology Transfer (DSSAT) crop model and semi-physical models (SPMs). The research integrates Sentinel-2 time-series data and ground data to generate comprehensive crop type maps. These maps offer insights into spatial variations in crop extent, growth stages and the leaf area index (LAI), serving as essential components for precise yield assessment. The classification of crops employed spectral matching techniques (SMTs) on Sentinel-2 time-series data, complemented by field surveys and ground data on crop management. The strategic identification of crop-cutting experiment (CCE) locations, based on a combination of crop type maps, soil data and weather parameters, further enhanced the precision of the study. A systematic comparison of three major crop yield estimation models revealed distinctive gaps in each approach. Machine learning models exhibit effectiveness in homogenous areas with similar cultivars, while the accuracy of a semi-physical model depends upon the resolution of the utilized data. The DSSAT model is effective in predicting yields at specific locations but faces difficulties when trying to extend these predictions to cover a larger study area. This research provides valuable insights for policymakers by providing near-real-time, high-resolution crop yield estimates at the local level, facilitating informed decision making in attaining food security.

show abstract

Predicting crop yields in Senegal using machine learning methods

Cited by 17 publications

References 91 publications

Modelling the impacts of water harvesting and climate change on rainfed maize yields in Senegal

Modelling the impacts of water harvesting and climate change on rainfed maize yields in Senegal

Machine Learning-Based Crop Yield Prediction in South India: Performance Analysis of Various Models

Optimizing Crop Yield Estimation through Geospatial Technology: A Comparative Analysis of a Semi-Physical Model, Crop Simulation, and Machine Learning Algorithms

Contact Info

Product

Resources

About