Multi-Crop Classification Using Feature Selection-Coupled Machine Learning Classifiers Based on Spectral, Textural and Environmental Features

Abstract

Machine learning (ML) classifiers have been widely used in the field of crop classification. However, having inputs that include a large number of complex features increases not only the difficulty of data collection but also reduces the accuracy of the classifiers. Feature selection (FS), which can availably reduce the number of features by selecting and reserving the most essential features for crop classification, is a good tool to solve this problem effectively. Different FS methods, however, have dissimilar effects on various classifiers, so how to achieve the optimal combination of FS methods and classifiers to meet the needs of high-precision recognition of multiple crops remains an open question. This paper intends to address this problem by coupling the analysis of three FS methods and six classifiers. Spectral, textual, and environmental features are firstly extracted as potential classification indexes from time-series remote sensing images from France. Then, three FS methods are used to obtain feature subsets and combined with six classifiers for coupling analysis. On this basis, 18 multi-crop classification models (FS–ML models) are constructed. Additionally, six classifiers without FS are constructed for comparison. The training set and the validation set for these models are constructed by using the Kennard-Stone algorithm with 70% and 30% of the samples, respectively. The performance of the classification model is evaluated by Kappa, F1-score, accuracy, and other indicators. The results show that different FS methods have dissimilar effects on various models. The best FS–ML model is RFAA+-RF, and its Kappa coefficient can reach 0.7968, which is 0.33–46.67% higher than that of other classification models. The classification results are highly dependent on the original classification index sets. Hence, the reasonability of combining spectral, textural, and environmental indexes is verified by comparing them with the single feature index set. The results also show that the classification strategy combining spectral, textual, and environmental indexes can effectively improve the ability of crop recognition, and the Kappa coefficient is 9.06–65.52% higher than that of the single unscreened feature set.

Precision mapping of snail habitat in lake and marshland areas: integrating environmental and textural indicators using Random Forest modeling

“…The superior performance of the baseline model can be attributed to its comprehensive evaluation of spatial factors associated with snail habitats and its consideration of seasonal aspects of reproduction. Among these factors, texture information has been shown in past studies to help models distinguish between different vegetation types [10,31]. The dominant snail habitat community, Cyperaceous, exhibits speci c patterns or structures at the textural scale, and incorporating textural information helps capture these differences.…”

“…Remote sensing images capture various textural attributes re ecting the spatial distribution structure of ground objects [9]. These attributes are invaluable for discerning the surface characteristics of distinct features [10]. Snail habitats often exhibit unique land surface features identi able through these textural attributes.…”

Bi-Objective Crop Mapping from Sentinel-2 Images Based on Multiple Deep Learning Networks

“…Phenology refers to the periodic changes with a certain pattern formed by organisms under the influence of various external environmental conditions, such as temperature and humidity, over a long period. Different crops usually have different phenological information, and the same crop has different phenological information in different regions [6]. From Xu and Fu [47], we obtained information on the main crops and their phenology in the study area.…”

“…Accurate mapping of paddy rice and winter wheat, especially during the growing seasons, is of great importance for maintaining food security and supporting the formulation of agricultural policies [5]. Traditional mapping of paddy rice and winter wheat requires many field surveys, which consumes considerable time and human resources with, however, low data quality [6].…”

Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity

“…The F1 score is aimed at dichotomies and reflects the classification effect of target-type crops, which is the harmonic value of recall and precision. Additionally, accuracy signifies the percentage of the correctly predicted rate of the whole sample [49]. The kappa coefficient is a comprehensive index to evaluate the classification performance of the model as a whole.…”