Estimation of Potato Yield Using Satellite Data at a Municipal Level: A Machine Learning Approach

Pablo Salvador,Diego Gómez,Julia Sanz,José Luis Casanova

doi:10.3390/ijgi9060343

Pablo Salvador, Diego Gómez + Show 2 more

Open Access

https://doi.org/10.3390/ijgi9060343

Copy DOI

Abstract

Crop growth modeling and yield forecasting are essential to improve food security policies worldwide. To estimate potato (Solanum tubersum L.) yield over Mexico at a municipal level, we used meteorological data provided by the ERA5 (ECMWF Re-Analysis) dataset developed by the Copernicus Climate Change Service, satellite imagery from the TERRA platform, and field information. Five different machine learning algorithms were used to build the models: random forest (rf), support vector machine linear (svmL), support vector machine polynomial (svmP), support vector machine radial (svmR), and general linear model (glm). The optimized models were tested using independent data (2017 and 2018) not used in the training and optimization phase (2004–2016). In terms of percent root mean squared error (%RMSE), the best results were obtained by the rf algorithm in the winter cycle using variables from the first three months of the cycle (R2 = 0.757 and %RMSE = 18.9). For the summer cycle, the best performing model was the svmP which used the first five months of the cycle as variables (R2 = 0.858 and %RMSE = 14.9). Our results indicated that adding predictor variables of the last two months before the harvest did not significantly improved model performances. These results demonstrate that our models can predict potato yield by analyzing the yield of the previous year, the general conditions of NDVI, meteorology, and information related to the irrigation system at a municipal level.

Highlights

Potato (Solanum tuberosum L.) is a crop that originated from the Andean region [1]
These results demonstrate that our models can predict potato yield by analyzing the yield of the previous year, the general conditions of normalized difference vegetation index (NDVI), meteorology, and information related to the irrigation system at a municipal level
In terms of %RMSE, the best machine learning (ML) algorithm during the winter cycle was the rf using the predictors corresponding to the 3-month scenario

Summary

Introduction

Potato (Solanum tuberosum L.) is a crop that originated from the Andean region [1] It is the most important non-grain crop worldwide [2] and the fourth-largest food crop after rice, wheat, and maize [3,4]. Potato produces more nutritious food, quicker, on less land and in harsher climates than any other major crop [2]. It plays a key role in food security strategies being grown and consumed in underprivileged areas [5]. In this sense, millions of farmers rely on potatoes as a source of food and economical support. Potato global trends indicate that developed countries are gradually reducing their potato production, whereas developing countries are increasing it [5,6]

Objectives

Methods

Results

Discussion

Conclusion