Recognition of the Bare Soil Using Deep Machine Learning Methods to Create Maps of Arable Soil Degradation Based on the Analysis of Multi-Temporal Remote Sensing Data

Abstract

The detection of degraded soil distribution areas is an urgent task. It is difficult and very time consuming to solve this problem using ground methods. The modeling of degradation processes based on digital elevation models makes it possible to construct maps of potential degradation, which may differ from the actual spatial distribution of degradation. The use of remote sensing data (RSD) for soil degradation detection is very widespread. Most often, vegetation indices (indicative botany) have been used for this purpose. In this paper, we propose a method for constructing soil maps based on a multi-temporal analysis of the bare soil surface (BSS). It is an alternative method to the use of vegetation indices. The detection of the bare soil surface was carried out using the spectral neighborhood of the soil line (SNSL) technology. For the automatic recognition of BSS on each RSD image, computer vision based on deep machine learning (neural networks) was used. A dataset of 244 BSS distribution masks on 244 Landsat 4, 5, 7, and 8 scenes over 37 years was developed. Half of the dataset was used as a training sample (Landsat path/row 173/028). The other half was used as a test sample (Landsat path/row 174/027). Binary masks were sufficient for recognition. For each RSD pixel, value “1” was set when determining the BSS. In the absence of BSS, value “0” was set. The accuracy of the machine prediction of the presence of BSS was 75%. The detection of degradation was based on the average long-term spectral characteristics of the RED and NIR bands. The coefficient Cmean, which is the distance of the point with the average long-term values of RED and NIR from the origin of the spectral plane RED/NIR, was calculated as an integral characteristic of the mean long-term values. Higher long-term average values of spectral brightness served as indicators of the spread of soil degradation. To test the method of constructing soil degradation maps based on deep machine learning, an acceptance sample of 133 Landsat scenes of path/row 173/026 was used. On the territory of the acceptance sample, ground verifications of the maps of the coefficient Cmean were carried out. Ground verification showed that the values of this coefficient make it possible to estimate the content of organic matter in the plow horizon (R2 = 0.841) and the thickness of the humus horizon (R2 = 0.8599). In total, 80 soil pits were analyzed on an area of 649 ha on eight agricultural fields. Type I error (false positive) of degradation detection was 17.5%, and type II error (false negative) was 2.5%. During the determination of the presence of degradation by ground methods, 90% of the ground data coincided with the detection of degradation from RSD. Thus, the quality of machine learning for BSS recognition is sufficient for the construction of soil degradation maps. The SNSL technology allows us to create maps of soil degradation based on the long-term average spectral characteristics of the BSS.

Updating of the Archival Large-Scale Soil Map Based on the Multitemporal Spectral Characteristics of the Bare Soil Surface Landsat Scenes

“…Based on the dataset, it is possible to carry out machine learning and automate the filtering of RSD. This problem was solved by the authors based on the development and application of a neural network [93].…”

“…The Use of a Neural Network in the Recognition of BSS The creation and application of a neural network for BSS recognition is described in detail in 2022 [93]. The method consists of training a neural network based on a dataset.…”

“…The authors showed that a "tasseled cap" can be built not only for an RSD frame but also for each RSD pixel based on the totality of the received spectral values of RED and NIR for 30 or more years on the same type of RSD [34] (Figure 2a). As a result, an MSL can be constructed [34,112] (Figure 2). Since the BSS multitemporal characteristics also take the form of an ellipse, it is proposed to use the ellipse parameters of the multitemporal spectral values for calculating the single BSS multitemporal characteristics of each pixel.…”

“…The authors have developed several methods for processing multitemporal RSD series for soil mapping purposes [7,24,29,93]: a method of averaging VIs values, a method of frequency filtering VIs values, and a method of calculating soil line parameters. In the work of 2021 [7], it was suggested that the use of multitemporal BSS series on RSD is highly effective for correcting ASMs and constructing an updated soil map.…”

Multi-Dimensional Low-Rank with Weighted Schatten p-Norm Minimization for Hyperspectral Anomaly Detection

“…Compared with conventional images such as RGB images, multispectral images, SAS images [1], and delay-Doppler images [2], hyperspectral images (HSIs) offer the advantage of capturing hundreds of contiguous spectral bands of the same scene. This unique characteristic of HSI proves to be beneficial for target detection and finds wide applications in various fields such as land cover classification [3][4][5], mineral survey [6][7][8], environmental protection [9][10][11], and other applications [12][13][14][15][16][17][18]. In hyperspectral target detection, when the target information is unknown, the unsupervised processing of the target detection is called anomaly detection.…”