Comparing Machine Learning Approaches for Predicting Spatially Explicit Life Cycle Global Warming and Eutrophication Impacts from Corn Production

Xiaobo Xue Romeiko,Zhijian Guo,Eun Kyung Lee,Yulei Pang,Xuesong Zhang

doi:10.3390/su12041481

Abstract

Agriculture ranks as one of the top contributors to global warming and nutrient pollution. Quantifying life cycle environmental impacts from agricultural production serves as a scientific foundation for forming effective remediation strategies. However, methods capable of accurately and efficiently calculating spatially explicit life cycle global warming (GW) and eutrophication (EU) impacts at the county scale over a geographic region are lacking. The objective of this study was to determine the most efficient and accurate model for estimating spatially explicit life cycle GW and EU impacts at the county scale, with corn production in the U.S.’s Midwest region as a case study. This study compared the predictive accuracies and efficiencies of five distinct supervised machine learning (ML) algorithms, testing various sample sizes and feature selections. The results indicated that the gradient boosting regression tree model built with approximately 4000 records of monthly weather features yielded the highest predictive accuracy with cross-validation (CV) values of 0.8 for the life cycle GW impacts. The gradient boosting regression tree model built with nearly 6000 records of monthly weather features showed the highest predictive accuracy with CV values of 0.87 for the life cycle EU impacts based on all modeling scenarios. Moreover, predictive accuracy was improved at the cost of simulation time. The gradient boosting regression tree model required the longest training time. ML algorithms demonstrated to be one million times faster than the traditional process-based model with high predictive accuracy. This indicates that ML can serve as an alternative surrogate of process-based models to estimate life-cycle environmental impacts, capturing large geographic areas and timeframes.

Highlights

Meeting continuously increasing food and fuel demands while protecting environmental integrity is a grand challenge
Both cross-validation (CV) correlation and R2 values of S1A were larger than those of S1B for the life cycle global warming (GW)
While machine learning approaches were suggested as alternative approaches for predicting the life cycle environmental impacts of agricultural production, no studies yet identified the appropriate sample sizes and most suitable machine learning for predicting spatially and temporally explicit life cycle environmental impacts

Summary

Introduction

Meeting continuously increasing food and fuel demands while protecting environmental integrity is a grand challenge. Agriculture as the primary stage for food and fuel production is associated with a range of environmental pollution issues ranging from global warming to nutrient degradation. Agriculture contributes to 8% of national greenhouse gases (GHGs) [1] and ranks as a leading contributor to nutrient pollution nationally and globally [2,3,4]. The continuous increasing of food and fuel demands accompanied by population growth, energy and water shortages, and weather unpredictability, will further accelerate environmental pollution from agricultural expansion [6,7,8,9,10]. Food production ranks as a top contributor to water quality degradation in the form of eutrophication and hypoxia. To effectively mitigate agricultural pollution, it is urgent to accurately and rapidly assess the environmental impacts of agriculture

Objectives

Results

Discussion

Conclusion