Advanced GIS and RS Applications for Soil and Land Degradation Assessment and Mapping

As soil erosion is still a global threat to soil resources, the estimation of soil loss, particularly at a spatiotemporal setting, is still an existing challenge. The primary aim of our study is the assessment of changes in soil erosion potential in Hungary from 1990 to 2018, induced by the changes in land use and land cover based on CORINE Land Cover data. The modeling scheme included the application and cross-valuation of two internationally applied methods, the Universal Soil Loss Equation (USLE) and the Pan-European Soil Erosion Risk Assessment (PESERA) models. Results indicate that the changes in land cover resulted in a general reduction in predicted erosion rates, by up to 0.28 t/ha/year on average. Analysis has also revealed that the combined application of the two models has reduced the occurrence of extreme predictions, thus, increasing the robustness of the method. Random Forest regression analysis has revealed that the differences between the two models are mainly driven by their sensitivity to slope and land cover, followed by soil parameters. The resulting spatial predictions can be readily applied for qualitative spatial analysis. However, the question of extreme predictions still indicates that quantitative use of the output results should only be carried out with sufficient care. Full article

Inland excess water is temporary water inundation that occurs in flat-lands due to both precipitation and groundwater emerging on the surface as substantial sources. Inland excess water is an interrelated natural and human induced land degradation phenomenon, which causes several problems in the flat-land regions of Hungary covering nearly half of the country. Identification of areas with high risk requires spatial modelling, that is mapping of the specific natural hazard. Various external environmental factors determine the behavior of the occurrence, frequency of inland excess water. Spatial auxiliary information representing inland excess water forming environmental factors were taken into account to support the spatial inference of the locally experienced inland excess water frequency observations. Two hybrid spatial prediction approaches were tested to construct reliable maps, namely Regression Kriging (RK) and Random Forest with Ordinary Kriging (RFK) using spatially exhaustive auxiliary data on soil, geology, topography, land use, and climate. Comparing the results of the two approaches, we did not find significant differences in their accuracy. Although both methods are appropriate for predicting inland excess water hazard, we suggest the usage of RFK, since (i) it is more suitable for revealing non-linear and more complex relations than RK, (ii) it requires less presupposition on and preprocessing of the applied data, (iii) and keeps the range of the reference data, while RK tends more heavily to smooth the estimations, while (iv) it provides a variable rank, providing explicit information on the importance of the used predictors. Full article

Gully erosion is one of the main processes of soil degradation, representing 50%–90% of total erosion at basin scales. Thus, its precise characterization has received growing attention in recent years. Geomatics techniques, mainly photogrammetry and LiDAR, can support the quantitative analysis of gully development. This paper deals with the application of these techniques using aerial photographs and airborne LiDAR data available from public database servers to identify and quantify gully erosion through a long period (1980–2016) in an area of 7.5 km² in olive groves. Several historical flights (1980, 1996, 2001, 2005, 2009, 2011, 2013 and 2016) were aligned in a common coordinate reference system with the LiDAR point cloud, and then, digital surface models (DSMs) and orthophotographs were obtained. Next, the analysis of the DSM of differences (DoDs) allowed the identification of gullies, the calculation of the affected areas as well as the estimation of height differences and volumes between models. These analyses result in an average depletion of 0.50 m and volume loss of 85000 m³ in the gully area, with some periods (2009–2011 and 2011–2013) showing rates of 10,000–20,000 m³/year (20–40 t/ha*year). The manual edition of DSMs in order to obtain digital elevation models (DTMs) in a detailed sector has facilitated an analysis of the influence of this operation on the erosion calculations, finding that it is not significant except in gully areas with a very steep shape. Full article

Gullies reduce both the quality and quantity of productive land, posing a serious threat to sustainable agriculture, hence, food security. Machine Learning (ML) algorithms are essential tools in the identification of gullies and can assist in strategic decision-making relevant to soil conservation. Nevertheless, accurate identification of gullies is a function of the selected ML algorithms, the image and number of classes used, i.e., binary (two classes) and multiclass. We applied Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Random Forest (RF) on a Systeme Pour l’Observation de la Terre (SPOT-7) image to extract gullies and investigated whether the multiclass (m) approach can offer better classification accuracy than the binary (b) approach. Using repeated k-fold cross-validation, we generated 36 models. Our findings revealed that, of these models, both RFb (98.70%) and SVMm (98.01%) outperformed the LDA in terms of overall accuracy (OA). However, the LDAb (99.51%) recorded the highest producer’s accuracy (PA) but had low corresponding user’s accuracy (UA) with 18.5%. The binary approach was generally better than the multiclass approach; however, on class level, the multiclass approach outperformed the binary approach in gully identification. Despite low spectral resolution, the pan-sharpened SPOT-7 product successfully identified gullies. The proposed methodology is relatively simple, but practically sound, and can be used to monitor gullies within and beyond the study region. Full article

Sonar survey of shallow water bodies has challenged scientists for a long time. Although these water courses are small, still they have an increasing ecological, touristic and economical role. As maritime sonars are non-ideal tools for shallow waters, the bathymetric survey of these rivers has been taken with cross-sectional methods. Due to recent developments, interferometric surveying technology have also burst into the market of recreational-grade fish-finders. The objective of the current study was the development of a novel, complex and integrated surveying technique which is affordable, robust and applicable even at low water levels. A recreational-grade sonar system was assembled and mounted on a double-hull vessel and connected with a geodetic Global Navigation Satellite System (GNSS) device. We have developed a novel software which enables the bridging between a closed sonar file format and the commonly used Geographic Information System (GIS) datasets. As a result, the several month-long conventional bathymetric survey of the 146 km-long reach of the Drava River was reduced to 20 days and provided channel bathymetry of many orders of magnitude higher than the classical methods. Additionally, a large number of spatial derivatives were generated which enables the analysis of channel morphology, textural variation of channel sediments and the accurate delineation of navigational routes. Full article

Environmental covariates are fundamental inputs of digital soil mapping (DSM) based on the soil–environment relationship. It is normal to have invalid values (or recorded as NoData value) in individual environmental covariates in some regions over an area, especially over a large area. Among the two main existing ways to deal with locations with invalid environmental covariate data in DSM, the location-skipping scheme does not predict these locations and, thus, completely ignores the potentially useful information provided by valid covariate values. The void-filling scheme may introduce errors when applying an interpolation algorithm to removing NoData environmental covariate values. In this study, we propose a new scheme called FilterNA that conducts DSM for each individual location with NoData value of a covariate by using the valid values of other covariates at the location. We design a new method (SoLIM-FilterNA) combining the FilterNA scheme with a DSM method, Soil Land Inference Model (SoLIM). Experiments to predict soil organic matter content in the topsoil layer in Anhui Province, China, under different test scenarios of NoData for environmental covariates were conducted to compare SoLIM-FilterNA with the SoLIM combined with the void-filling scheme, the original SoLIM with the location-skipping scheme, and random forest. The experimental results based on the independent evaluation samples show that, in general, SoLIM-FilterNA can produce the lowest errors with a more complete spatial coverage of the DSM result. Meanwhile, SoLIM-FilterNA can reasonably predict uncertainty by considering the uncertainty introduced by applying the FilterNA scheme. Full article

In this paper, the preliminary results of an integrated geomorphological study carried out in a 1.6 ha catchment area located on the eastern side of the Crati River valley (northern Calabria, South Italy) have been presented. An orthophoto and shaded relief map of the study catchment, obtained by 288 unmanned aerial vehicle (UAV) images, integrated with field geomorphological surveys have been used to produce a detailed map of landslides and water erosion phenomena. The study area is characterized by active morphodynamic processes that result in the occurrence of water erosion phenomena and several landslides. In particular, 29 slides and 37 earth slides that evolve into earth flows have been recognized. Spatial and temporal development of geomorphic processes (erosion/depletion and sedimentation/accumulation) have affected the catchment area in the last seven years. Indeed, the comparison between light detection and ranging digital terrain models (LiDAR-DTM) of 2012 and UAV-DTM of 2019 showed depletion values between −0.01 and –5.76 m, with a mean value of −0.96 m; whereas for the accumulation the mean value is 0.94 m, with a maximum thickness of the deposited material of about 2.98 m. The results obtained highlight the usefulness of the methodology to provide detailed information on geomorphic processes and related short-term landscape development in a small drainage basin. Full article

Grassland coverage, aboveground net primary production (ANPP), and species composition are used as indicators of grassland degradation. However, soil salinization deficiency, which is also a factor of grassland degradation, is rarely used in grassland degradation assessment in semiarid regions. We assessed grassland degradation by its quality, quantity, and spatial pattern over semiarid west Jilin, China. Considering soil salinization in west Jilin, electrical conductivity (EC) is used as an index with ANPP to assess grassland degradation. First, the spatial distribution of the grassland was measured with information mined from multi-temporal remote sensing images using an object-based image analysis combined with classification and decision tree methods. Second, with 166 field samples, we utilized the random forest (RF) algorithm as the variable selection and regression method for predicting EC and ANPP. Finally, we created a new grassland degradation model (GDM) based on ANPP and EC. The results showed the R² (0.91) and RMSE (0.057 mS/cm) of the EC model were generally highest and lowest when the ntree was 400; the ANPP model was optimal (R² = 0.85 and RMSE = 15.81 gC/m²) when the ntree was 600. Grassland area of west Jilin was 609.67 × 10³ ha in 2017, there were 373.79 × 10³ ha of degraded grassland, with 210.47 × 10³ ha being intensively degraded. This paper surpasses past limitations of excessive reliance on vegetation index to construct a grassland degradation model which considers the characteristics of the study area and soil salinity. The results confirm the positive influence of the ecological conservation projects sponsored by the government. The research outcome could offer supporting data for decision making to help alleviate grassland degradation and promote the rehabilitation of grassland vegetation. Full article

Understanding the spatial variability of soil health and identifying areas that share similar soil properties can help nations transition to sustainable agricultural practices. This information is particularly applicable to management decisions such as tillage, nutrient application, and soil and water conservation. This study evaluated the spatial variability and derived the optimal number of spatially contiguous regions of Nigeria’s 774 Local Government Areas (LGAs) using three soil health indicators, organic carbon (OC), bulk density (BD) and total nitrogen (TN) extracted from the Africa Soil Information Service database. Missing data were imputed using the random forest imputation method with topography and normalized difference vegetation index (NDVI) as auxiliary variables. Using an exponential covariance function, the spatial ranges for BD, SN, and OC were calculated as 18, 42, and 60 km, respectively. These were the maximum distances at which there was no correlation between the sample data points. This finding suggests that OC has high variability across Nigeria as compared with other tested indicators. The ordinary kriging (OK) technique revealed spatial dependency (positive correlation) among TN and OC on interpolated surfaces, with high values in the southern part of the county and low values in the north. The BD values were also high in the northern regions where the soils are sandy; correspondingly, TN and OC had low values. The “regionalization with dynamically constrained agglomerative clustering and partitioning” (REDCAP) technique was used to divide LGAs into a possible number of regions while optimizing a sum of squares deviation (SSD). Optimal division was not observed in the resulting number of regional partitions. Conducting the Markov Chain Monte Carlo (MCMC) method on within-zone heterogeneity (WZH) revealed three partitions (two, five, and 15 regions) as optimal, in other words, there would be no significant change in WZH after three partitions. Ensuring a proper understanding of soil spatial variability and heterogeneities (or homogeneities) could facilitate agricultural planning that combines or merges state and local governments that share the same soil health properties, rather than basing decisions on geopolitical, racial, or ethnoreligious factors. The findings of this study could be applied to understand the importance of soil heterogeneities in hydrologic modeling applications. In addition, the findings may aid decision-making bodies such as the United Nations’ Food and Agricultural Organization, the International Fund for Agricultural Development, or the World Bank in their efforts to alleviate poverty, meet future food needs, mitigate the impacts of climate change, and provide financial funding through sustainable agriculture and intervention in developing countries such as Nigeria. Full article

Quickly and efficiently monitoring soil nutrient contents using remote sensing technology is of great significance for farmland soil productivity, food security and sustainable agricultural development. Current research has been conducted to estimate and map soil nutrient contents in large areas using hyper-spectral techniques, however, it is difficult to obtain accurate estimates. In order to improve the estimation accuracy of soil nutrient contents, we introduced a GA-BPNN method, which combined a back propagation neural network (BPNN) with the genetic algorithm optimization (GA). This study was conducted in Guangdong, China, based on soil nutrient contents and hyperspectral data. The prediction accuracies from a partial least squares regression (PLSR), BPNN and GA-BPNN were compared using field observations. The results showed that (1) Among three methods, the GA-BPNN provided the most accurate estimates of soil total nitrogen (TN), total phosphorus (TP) and total potassium (TK) contents; (2) Compared with the BPNN models, the GA-BPNN models significantly improved the estimation accuracies of the soil nutrient contents by decreasing the relative root mean square error (RRMSE) values by 15.9%, 5.6% and 20.2% at the sample point level, and 20.1%, 16.5% and 47.1% at the regional scale for TN, TP and TK, respectively. This indicated that by optimizing the parameters of BPNN, the GA-BPNN provided greater potential to improving the estimation; and (3) Soil TK content could be more accurately mapped by the GA-BPNN method using HuanJing-1A Hyperspectral Imager (HJ-1A HSI) (manufacturer: China Aerospace Science and Technology Corporation; Beijing, China) data with a RRMSE value of 20.37% than the soil TN and TP with the RRMSE values of 40.41% and 34.71%, respectively. This implied that the GA-BPNN model provided the potential to map the soil TK content for the large area. The research results provided an important reference for high-accuracy prediction of soil nutrient contents. Full article

Accurate digital soil mapping (DSM) of soil organic carbon (SOC) is still a challenging subject because of its spatial variability and dependency. This study is aimed at comparing six typical methods in three types of DSM techniques for SOC mapping in an area surrounding Changchun in Northeast China. The methods include ordinary kriging (OK) and geographically weighted regression (GWR) from geostatistics, support vector machines for regression (SVR) and artificial neural networks (ANN) from machine learning, and geographically weighted regression kriging (GWRK) and artificial neural networks kriging (ANNK) from hybrid approaches. The hybrid approaches, in particular, integrated the GWR from geostatistics and ANN from machine learning with the estimation of residuals by ordinary kriging, respectively. Environmental variables, including soil properties, climatic, topographic, and remote sensing data, were used for modeling. The mapping results of SOC content from different models were validated by independent testing data based on values of the mean error, root mean squared error and coefficient of determination. The prediction maps depicted spatial variation and patterns of SOC content of the study area. The results showed the accuracy ranking of the compared methods in decreasing order was ANNK, SVR, ANN, GWRK, OK, and GWR. Two-step hybrid approaches performed better than the corresponding individual models, and non-linear models performed better than the linear models. When considering the uncertainty and efficiency, ML and two-step approach are more suitable than geostatistics in regional landscapes with the high heterogeneity. The study concludes that ANNK is a promising approach for mapping SOC content at a local scale. Full article

Watersheds represent natural units of social–ecological systems and affect crop productivity. Extreme weather events accelerate the natural erosion process by triggering more landslides in watersheds. To achieve the land degradation neutrality set up by the UN’s Sustainable Development Goals, it is necessary to assess and map spatiotemporal landslides in watersheds. This paper proposes an innovative approach to calculating the instability index by preparing an annual landslide inventory, determining the optimum sub-watershed, compensating for shadow effects on the time series of the landslide area ratio, and classifying the standard deviations to different levels of instability. Taking the Qingquan watershed as an example, the instability index calculated for 22 sub-watersheds makes it possible to identify hot spots that are prone to collapse. This new index can also be used to evaluate the effectiveness of watershed management before and after completion of a specific engineering project, as well as to update the latest upriver situation to evaluate current management practices and develop strategies for future planning. Based on this new approach, the Soil and Water Conservation Bureau of Taiwan assesses the stability of 28 watersheds, and the results are made available on the Big Geospatial Information System. Full article