High Resolution Mapping of Soil Properties Using Remote Sensing Variables in South-Western Burkina Faso: A Comparison of Machine Learning and Multiple Linear Regression Models

Abstract

Accurate and detailed spatial soil information is essential for environmental modelling, risk assessment and decision making. The use of Remote Sensing data as secondary sources of information in digital soil mapping has been found to be cost effective and less time consuming compared to traditional soil mapping approaches. But the potentials of Remote Sensing data in improving knowledge of local scale soil information in West Africa have not been fully explored. This study investigated the use of high spatial resolution satellite data (RapidEye and Landsat), terrain/climatic data and laboratory analysed soil samples to map the spatial distribution of six soil properties–sand, silt, clay, cation exchange capacity (CEC), soil organic carbon (SOC) and nitrogen–in a 580 km2 agricultural watershed in south-western Burkina Faso. Four statistical prediction models–multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM), stochastic gradient boosting (SGB)–were tested and compared. Internal validation was conducted by cross validation while the predictions were validated against an independent set of soil samples considering the modelling area and an extrapolation area. Model performance statistics revealed that the machine learning techniques performed marginally better than the MLR, with the RFR providing in most cases the highest accuracy. The inability of MLR to handle non-linear relationships between dependent and independent variables was found to be a limitation in accurately predicting soil properties at unsampled locations. Satellite data acquired during ploughing or early crop development stages (e.g. May, June) were found to be the most important spectral predictors while elevation, temperature and precipitation came up as prominent terrain/climatic variables in predicting soil properties. The results further showed that shortwave infrared and near infrared channels of Landsat8 as well as soil specific indices of redness, coloration and saturation were prominent predictors in digital soil mapping. Considering the increased availability of freely available Remote Sensing data (e.g. Landsat, SRTM, Sentinels), soil information at local and regional scales in data poor regions such as West Africa can be improved with relatively little financial and human resources.

Remote-sensing data processing with the multivariate regression analysis method for iron mineral resource potential mapping: a case study in the Sarvian area, central Iran

“…multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM) and stochastic gradient boosting (SGB), to study soil properties in southwestern Burkina Faso. The results of all four methods are confirmed by Forkuor et al (2017), who stated that other methods are preferable in comparison with methods based on regression according to the model performances statistics. This statement can obviously not be accurate in iron ore exploration of the Sarvian area.…”

“…The more kernels can locate the classes with maximum distance from each other, the greater the accuracy with which the classification will be done. This refers to the maximum distance between the separator screen and the closest samples of each class (Forkuor et al, 2017;Cheng and Bao, 2014).…”

“…Due to the fact that the model predicts the results according to the data as well as the relationships between the data, the results are closer to reality. Forkuor et al (2017) used four methods, i.e. multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM) and stochastic gradient boosting (SGB), to study soil properties in southwestern Burkina Faso.…”

“…The complexities of mineral exploration can be solved by using remote-sensing techniques in the early stages of mineral exploration for the reconnaissance of target areas with the goal of continuing exploratory operations. One of the most recognizable uses with remote sensing is mineral exploration and the identification of various geological structures, faults and lineaments, geological units, alterations, indicator, and tracer minerals (Melesse et al, 2007;Carranza, 2008;Abedi et al, 2013;Golshadi et al, 2016 andMansouri, 2012). The factors mentioned play important roles for recognizing mineralization in the region of interest; so the identification of these factors saves time and cost as well as giving a more precise result (Xiong and Zuo, 2017).…”

Risk prediction in life insurance industry using supervised learning algorithms

“…In other words, the equation is used to predict the response variable based on the values of the explanatory variables collectively [39].…”