Teasing Apart Silvopasture System Components Using Machine Learning for Optimization

Tulsi P Kharel,Dirk Philipp,Phillip R Owens,Thomas J Sauer,Amanda J Ashworth,Andrew L Thomas

doi:10.3390/soilsystems5030041

Abstract

Silvopasture systems combine tree and livestock production to minimize market risk and enhance ecological services. Our objective was to explore and develop a method for identifying driving factors linked to productivity in a silvopastoral system using machine learning. A multi-variable approach was used to detect factors that affect system-level output (i.e., plant production (tree and forage), soil factors, and animal response based on grazing preference). Variables from a three-year (2017–2019) grazing study, including forage, tree, soil, and terrain attribute parameters, were analyzed. Hierarchical variable clustering and random forest model selected 10 important variables for each of four major clusters. A stepwise multiple linear regression and regression tree approach was used to predict cattle grazing hours per animal unit (h ha−1 AU−1) using 40 variables (10 per cluster) selected from 130 total variables. Overall, the variable ranking method selected more weighted variables for systems-level analysis. The regression tree performed better than stepwise linear regression for interpreting factor-level effects on animal grazing preference. Cattle were more likely to graze forage on soils with Cd levels <0.04 mg kg−1 (126% greater grazing hours per AU), soil Cr <0.098 mg kg−1 (108%), and a SAGA wetness index of <2.7 (57%). Cattle also preferred grazing (88%) native grasses compared to orchardgrass (Dactylis glomerata L.). The result shows water flow within the landscape position (wetness index), and associated metals distribution may be used as an indicator of animal grazing preference. Overall, soil nutrient distribution patterns drove grazing response, although animal grazing preference was also influenced by aboveground (forage and tree), soil, and landscape attributes. Machine learning approaches helped explain pasture use and overall drivers of grazing preference in a multifunctional system.

Highlights

IntroductionSilvopastoral systems combine agroforestry and pasture/livestock to maximize ecosystem services and mitigate risk by diversifying markets
The majority of variables were in cluster one, along with most terrain features, indicating terrain features are an important factor driving the majority of variability in the silvopasture data set
We further explored soil Cd and its relationship with forage parameters, and results suggested that forage yield, NDF, and acid digestible fiber (ADF) decreased with increasing soil Cd contents at this site

Summary

Introduction

Silvopastoral systems combine agroforestry and pasture/livestock to maximize ecosystem services and mitigate risk by diversifying markets. It is a complex system, with factors such as soil, topography, tree species, and forage species interacting to influence net primary productivity, as well as ecosystem services [1,2,3,4]. Topography, characterized by terrain features, controls the spatial distribution of soil water and associated nutrients, affecting the quality and quantity of forage production, as well as grazing preference spatially and temporally. Classical statistical analysis often fails to capture the effect of nonlinear factors and their interaction once the number of variables increases in the model

Objectives

Methods

Results

Discussion

Conclusion