Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis

A low-cost approach for soil moisture prediction using multi-sensor data and machine learning algorithm

A high-resolution soil moisture prediction method has recently gained its importance in various fields such as forestry, agricultural and land management. However, accurate, robust and non- cost prohibitive spatially monitoring of soil moisture is challenging. In this research, a new approach involving the use of advance machine learning (ML) models, and multi-sensor data fusion including Sentinel-1(S1) C-band dual polarimetric synthetic aperture radar (SAR), Sentinel-2 (S2) multispectral data, and ALOS Global Digital Surface Model (ALOS DSM) to predict precisely soil moisture at 10 m spatial resolution across research areas in Australia. The total of 52 predictor variables generated from S1, S2 and ALOS DSM data fusion, including vegetation indices, soil indices, water index, SAR transformation indices, ALOS DSM derived indices like digital model elevation (DEM), slope, and topographic wetness index (TWI). The field soil data from Western Australia was employed. The performance capability of extreme gradient boosting regression (XGBR) together with the genetic algorithm (GA) optimizer for features selection and optimization for soil moisture prediction in bare lands was examined and compared with various scenarios and ML models. The proposed model (the XGBR-GA model) with 21 optimal features obtained from GA was yielded the highest performance (R² = 0. 891; RMSE = 0.875%) compared to random forest regression (RFR), support vector machine (SVM), and CatBoost gradient boosting regression (CBR). Conclusively, the new approach using the XGBR-GA with features from combination of reliable free-of-charge remotely sensed data from Sentinel and ALOS imagery can effectively estimate the spatial variability of soil moisture. The described framework can further support precision agriculture and drought resilience programs via water use efficiency and smart irrigation management for crop production.

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

Estimation of the soil organic carbon (SOC) content is of utmost importance in understanding the chemical, physical, and biological functions of the soil. This study proposes machine learning algorithms of support vector machines (SVM), artificial neural networks (ANN), regression tree, random forest (RF), extreme gradient boosting (XGBoost), and conventional deep neural network (DNN) for advancing prediction models of SOC. Models are trained with 1879 composite surface soil samples, and 105 auxiliary data as predictors. The genetic algorithm is used as a feature selection approach to identify effective variables. The results indicate that precipitation is the most important predictor driving 14.9% of SOC spatial variability followed by the normalized difference vegetation index (12.5%), day temperature index of moderate resolution imaging spectroradiometer (10.6%), multiresolution valley bottom flatness (8.7%) and land use (8.2%), respectively. Based on 10-fold cross-validation, the DNN model reported as a superior algorithm with the lowest prediction error and uncertainty. In terms of accuracy, DNN yielded a mean absolute error of 0.59%, a root mean squared error of 0.75%, a coefficient of determination of 0.65, and Lin’s concordance correlation coefficient of 0.83. The SOC content was the highest in udic soil moisture regime class with mean values of 3.71%, followed by the aquic (2.45%) and xeric (2.10%) classes, respectively. Soils in dense forestlands had the highest SOC contents, whereas soils of younger geological age and alluvial fans had lower SOC. The proposed DNN (hidden layers = 7, and size = 50) is a promising algorithm for handling large numbers of auxiliary data at a province-scale, and due to its flexible structure and the ability to extract more information from the auxiliary data surrounding the sampled observations, it had high accuracy for the prediction of the SOC base-line map and minimal uncertainty.

Iterative Screening Methods for Identification of Chemical Compounds with Specific Values of Various Properties

Identification of chemical compounds having desirable properties is a central goal of screening campaigns. Iterative screening is a means of surveying a set of compounds, during which their property values are determined and used as feedback for regression models. Quantitative models that assess the relationships between chemical structures and property/activity are repeatedly updated through this type of cycle, and the efficient sampling of compounds for the subsequent test is a key factor in the early identification of target compounds. Nevertheless, methodological approaches to comparisons and to establishing the degree of extrapolation of sampled compounds, including the effects of applicability domains, are still required. In the present study, we conducted a series of virtual experiments to assess the characteristics of different iterative screening methods. Genetic algorithm-based partial least-squares regression, support vector regression, Bayesian optimization with Gaussian Process (GP), and batch-based Bayesian optimization with GP (GP_batch) were all compared, based on the analysis of one million compounds extracted from the ZINC database. Our results show that, irrespective of the diversity of the initial set of compounds, it was possible to identify a compound having the desired property value using the appropriate screening method. However, overall, the GP_batch method was found to be preferable when evaluating properties either which are difficult to predict or for which a key factor is present in the set of molecular descriptors.

An ensemble variable selection method for vibrational spectroscopic data analysis

Wavelength selection is a critical factor for pattern recognition of vibrational spectroscopic data. Not only does it alleviate the effect of dimensionality on an algorithm's generalization performance, but it also enhances the understanding and interpretability of multivariate classification models. In this study, a novel partial least squares discriminant analysis (PLSDA)-based wavelength selection algorithm, termed ensemble of bootstrapping space shrinkage (EBSS), has been devised for vibrational spectroscopic data analysis. In the algorithm, a set of subsets are generated from a data set using random sampling. For an individual subset, a feature space is determined by maximizing the expected 10-fold cross-validation accuracy with a weighted bootstrap sampling strategy. Then an ensemble strategy and a sequential forward selection method are applied to the feature spaces to select characteristic variables. Experimental results obtained from analysis of real vibrational spectroscopic data sets demonstrate that the ensemble wavelength selection algorithm can reserve stable and informative variables for the final modeling and improve predictive ability for multivariate classification models.

A new ensemble method for wavelength selection.

Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps

This review highlights and discusses critically various knowledge gaps in classification modelling using PLS-DA for high dimensional data.