Within-Field Yield Prediction in Cereal Crops Using LiDAR-Derived Topographic Attributes with Geographically Weighted Regression Models

Riley Eyre,John Lindsay,Ahmed Laamrani,Aaron Berg

doi:10.3390/rs13204152

Abstract

Accurate yield estimation and optimized agricultural management is a key goal in precision agriculture, while depending on many different production attributes, such as soil properties, fertilizer and irrigation management, the weather, and topography.The need for timely and accurate sensing of these inputs at the within field-scale has led to increased adoption of very high-resolution remote and proximal sensing technologies. With regard to topography attributes, greater attention is currently being devoted to LiDAR datasets (Light Detection and Ranging), mainly because numerous topographic variables can be derived at very high spatial resolution from these datasets. The current study uses LiDAR elevation data from agricultural land in southern Ontario, Canada to derive several topographic attributes such as slope, and topographic wetness index, which were then correlated to seven years of crop yield data. The effectiveness of each topographic derivative was independently tested using a moving-window correlation technique. Finally, the correlated derivatives were selected as explanatory variables for geographically weighted regression (GWR) models. The global coefficient of determination values (determined from an average of all the local relationships) were found to be R2 = 0.80 for corn, R2 = 0.73 for wheat, R2 = 0.71 for soybeans and R2 = 0.75 for the average of all crops. These results indicate that GWR models using topographic variables derived from LiDAR can effectively explain yield variation of several crop types on an entire-field scale.

Highlights

Precision agriculture technologies are increasingly dependent on accurate crop yield information in order to be effective
We would have multiple study locations for the identification and evaluation of the important topographic attributes for explaining crop yield variance, given the large number of years of yield data and that the data were collected among different crop types, we suggest that the attributes observed are still highly valuable for characterization of yield variance
This study, which included multiple years of yield data for several cereal crops demonstrated that topographic derivatives such as relative topographic position proved to be more predictive than elevation, which has been included in past studies investigating relationships between topography and crop yield

Summary

Introduction

Precision agriculture technologies are increasingly dependent on accurate crop yield information in order to be effective. Not all farmers are able to collect these data due to the initial cost or because of the technological knowledge required to extract and examine the data. This is especially true in developing regions where the use of yieldmonitoring technology is rare. Data protection and privacy rights can make it difficult to access annual yield data [1] In these cases, it would be beneficial to use proxies for crop yield that can be determined without the need for yield-monitoring technology that require more investment and time. Using topographic attributes may be a viable method for measuring within-field crop yield variability to identify low-yielding regions of cropland where ecologically beneficial land

Objectives

Results

Discussion

Conclusion