The Use of Deep Machine Learning for the Automated Selection of Remote Sensing Data for the Determination of Areas of Arable Land Degradation Processes Distribution

Abstract

Soil degradation processes are widespread on agricultural land. Ground-based methods for detecting degradation require a lot of labor and time. Remote methods based on the analysis of vegetation indices can significantly reduce the volume of ground surveys. Currently, machine learning methods are increasingly being used to analyze remote sensing data. In this paper, the task is set to apply deep machine learning methods and methods of vegetation indices calculation to automate the detection of areas of soil degradation development on arable land. In the course of the work, a method was developed for determining the location of degraded areas of soil cover on arable fields. The method is based on the use of multi-temporal remote sensing data. The selection of suitable remote sensing data scenes is based on deep machine learning. Deep machine learning was based on an analysis of 1028 scenes of Landsats 4, 5, 7 and 8 on 530 agricultural fields. Landsat data from 1984 to 2019 was analyzed. Dataset was created manually for each pair of “Landsat scene”/“agricultural field number”(for each agricultural field, the suitability of each Landsat scene was assessed). Areas of soil degradation were calculated based on the frequency of occurrence of low NDVI values over 35 years. Low NDVI values were calculated separately for each suitable fragment of the satellite image within the boundaries of each agricultural field. NDVI values of one-third of the field area and lower than the other two-thirds were considered low. During testing, the method gave 12.5% of type I errors (false positive) and 3.8% of type II errors (false negative). Independent verification of the method was carried out on six agricultural fields on an area of 713.3 hectares. Humus content and thickness of the humus horizon were determined in 42 ground-based points. In arable land degradation areas identified by the proposed method, the probability of detecting soil degradation by field methods was 87.5%. The probability of detecting soil degradation by ground-based methods outside the predicted regions was 3.8%. The results indicate that deep machine learning is feasible for remote sensing data selection based on a binary dataset. This eliminates the need for intermediate filtering systems in the selection of satellite imagery (determination of clouds, shadows from clouds, open soil surface, etc.). Direct selection of Landsat scenes suitable for calculations has been made. It allows automating the process of constructing soil degradation maps.

Survey on Machine Learning and Deep Learning Techniques for Agriculture Land

“…In this paper, we have systematically reviewed the stateof-art machine learning and deep learning techniques in remote sensing data analysis [67]. The deep learning techniques were originally rooted in machine learning fields for classification and recognition tasks, and they have only recently appeared in the remote sensing and geoscience community [30].…”

Implementation of a multi‐layered land degradation monitoring and forecasting framework toward integrated countermeasure planning in drylands

“…The tool's capacity to forecast future LD is based on machine learning (ML) models for forecasting future LD/SDS. The applications of ML to forecast LD (Grinand et al, 2020; Rukhovich et al, 2021; Torabi et al, 2021), as well as SDS (Boroughani et al, 2020; Jiao et al, 2021), have been recently demonstrated. We evaluated the ML‐LDT prototype over two study areas in the Indian Thar Desert and Inner Mongolia, China.…”

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

“…For such scales, the instruction on soil mapping of 1973 applies to the territory of Russia [1]. Often, instead of soil cover mapping, various methods of indicative botany were used in the form of analyses of vegetation indices [2][3][4][5][6][7]. An alternative to vegetation indices is the method of constructing soil maps based on the analysis of the bare soil surface [8][9][10][11][12][13][14].…”

“…Clouds masks are in open access [43]. The disadvantages of existing cloud masks require new filtering methods based on deep machine learning and computer vision [6,[44][45][46][47]. It can be assumed that the use of deep machine learning will make it possible to select the necessary satellite images.…”

“…Often, when degradation is recognized, sites with reduced yields are searched for [57,62,63]. When analyzing long-term observation series, areas are selected where a reduced yield is recorded most often [6,63,64]. It can be assumed that areas of agricultural fields with uniform spectral characteristics recorded over many years can be an indicator of the state of the soil cover.…”