Prediction of Soil Water Content and Electrical Conductivity Using Random Forest Methods with UAV Multispectral and Ground-Coupled Geophysical Data

Abstract

The volumetric water content (VWC) of soil is a critical parameter in agriculture, as VWC strongly influences crop yield, provides nutrients to plants, and maintains the microbes that are needed for the biological health of the soil. Measuring VWC is difficult, as it is spatially and temporally heterogeneous, and most agricultural producers use point measurements that cannot fully capture this parameter. Electrical conductivity (EC) is another soil parameter that is useful in agriculture, since it can be used to indicate soil salinity, soil texture, and plant nutrient availability. Soil EC is also very heterogeneous; measuring EC using conventional soil sampling techniques is very time consuming and often fails to capture the variability in EC at a site. In contrast to the point-based methods used to measure VWC and EC, multispectral data acquired with unmanned aerial vehicles (UAV) can cover large areas with high resolution. In agriculture, multispectral data are often used to calculate vegetation indices (VIs). In this research UAV-acquired VIs and raw multispectral data were used to predict soil VWC and EC. High-resolution geophysical methods were used to acquire more than 41,000 measurements of VWC and 8,000 measurements of EC in 18 traverses across a field that contained 56 experimental plots. The plots varied by crop type (corn, soybeans, and alfalfa) and drainage (no drainage, moderate drainage, high drainage). Machine learning was performed using the random forest method to predict VWC and EC using VIs and multispectral data. Prediction accuracy was determined for several scenarios that assumed different levels of knowledge about crop type or drainage. Results showed that multispectral data improved prediction of VWC and EC, and the best predictions occurred when both the crop type and degree of drainage were known, but drainage was a more important input than crop type. Predictions were most accurate in drier soil, which may be due to the lower overall variability of VWC and EC under these conditions. An analysis of which multispectral data were most important showed that NDRE, VARI, and blue band data improved predictions the most. The final conclusions of this study are that inexpensive UAV-based multispectral data can be used to improve estimation of heterogenous soil properties, such as VWC and EC in active agricultural fields. In this study, the best estimates of these properties were obtained when the agriculture parameters in a field were fairly homogeneous (one crop type and the same type of drainage throughout the field), although improvements were observed even when these conditions were not met. The multispectral data that were most useful for prediction were those that penetrated deeper into the soil canopy or were sensitive to bare soil.

Use of unmanned aerial vehicle-derived multi-spectral data for the early detection of multi-temporal maize leaf equivalent water thickness and fuel moisture content for the improved resilience of smallholder maize farming

“…The use of machine learning algorithms, such as the random forest (RF), support vector machines (SVM), and multiple linear regression, has have been proven to be instrumental in characterizing crop characteristics 33 . RF has proven to be a valuable regression model and is known for its efficiency in handling outliers, its ability to account for non-linear relationships between multiple variables, and its capacity to produce credible results, even with a small dataset, as was the case in this study 34 , 35 . The RF algorithm has high computational efficiency in processing non-parametric and high dimensional data while being sensitive to overfitting 35…”

“…33 RF has proven to be a valuable regression model and is known for its efficiency in handling outliers, its ability to account for non-linear relationships between multiple variables, and its capacity to produce credible results, even with a small dataset, as was the case in this study. 34,35 The RF algorithm has high computational efficiency in processing non-parametric and high dimensional data while being sensitive to overfitting. [35][36][37] The success of the RF regression model has been well-documented in recent literature.…”

Analysis of soybean varieties maturation using multispectral data

“…The vegetation index GNDVI is considered as effective in phenotyping soybean plants in various studies [13][14][15][16]. The blue spectral channel (wavelength 475 nm) also plays an important role in agricultural research [17][18][19][20]. The obtained data contribute to the study of latent characteristics of the varieties under consideration and accelerate the process of breeding new soybean varieties.…”

Investigation of the spatial and temporal variation of soil salinity using Google Earth Engine: a case study at Werigan–Kuqa Oasis, West China

“…RF is a bagging improvement that enhances variable selection 44 , Instead of selecting the optimal split among all characteristics at each node, RF randomly picks a subset of features to decide the www.nature.com/scientificreports/ split, this makes RF more resilient to noise and less prone to overfitting. In addition, RF can handle outliers very well 45 . The number of trees and predictor variables that the random forest model allows the decision tree to grow as large as it can without being trimmed is its critical factor.…”