scholarly journals Prediction of land degradation by Machine Learning Methods

2021 ◽  
Vol 25 (3) ◽  
pp. 353-362
Author(s):  
Vahid Habibi ◽  
Hassan Ahmadi ◽  
Mohammad Jaffari ◽  
Abolfazl Moeini
Keyword(s):  
Land Degradation ◽  
Land Surface ◽  
Ordinary Kriging ◽  
Total Error ◽  
Geographic Location ◽  
Degradation Index ◽  
Machine Learning Methods ◽  
Groundwater Condition ◽  
Combined Models ◽  
Input Variables

In this study, three models were used to monitor and predict the GWL and the land degradation index via the IMDPA method. In all models, 70% of the data was applied for training, while 30% of data were employed for testing and validation. Monthly rainfall, TWI index, the distance of the river, Geographic location was the inputs and the level of groundwater was the output of each method. we found that ANN has the highest efficiency, which agrees with other findings. We combined the results of ANN with Ordinary Kriging and produced a groundwater condition map. According to the potential desertification map and groundwater level index, the potential of desertification had become severe since 2002 and was at a rate of 60% of land area, which, due to incorrect land management in 2016, increased to almost 98% of the land surface in the study area. Using ANN, we predicted that around 99% of the area was severely degraded for 2017. We also used latitude and longitude as input variables which improved the model. In addition to the target variable, latitude and longitude play important roles in Ordinary Kriging and decreased the total error of two combined models.

scholarly journals Snow Depth Fusion Based on Machine Learning Methods for the Northern Hemisphere

2021 ◽  
Vol 13 (7) ◽  
pp. 1250
Author(s):  
Yanxing Hu ◽  
Tao Che ◽  
Liyun Dai ◽  
Lin Xiao
Keyword(s):  
Machine Learning ◽  
Northern Hemisphere ◽  
Snow Depth ◽  
Learning Algorithm ◽  
Random Forest Regression ◽  
Machine Learning Methods ◽  
Long Time ◽  
In Situ Observations ◽  
Input Variables

In this study, a machine learning algorithm was introduced to fuse gridded snow depth datasets. The input variables of the machine learning method included geolocation (latitude and longitude), topographic data (elevation), gridded snow depth datasets and in situ observations. A total of 29,565 in situ observations were used to train and optimize the machine learning algorithm. A total of five gridded snow depth datasets—Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) snow depth, Global Snow Monitoring for Climate Research (GlobSnow) snow depth, Long time series of daily snow depth over the Northern Hemisphere (NHSD) snow depth, ERA-Interim snow depth and Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) snow depth—were used as input variables. The first three snow depth datasets are retrieved from passive microwave brightness temperature or assimilation with in situ observations, while the last two are snow depth datasets obtained from meteorological reanalysis data with a land surface model and data assimilation system. Then, three machine learning methods, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest Regression (RFR), were used to produce a fused snow depth dataset from 2002 to 2004. The RFR model performed best and was thus used to produce a new snow depth product from the fusion of the five snow depth datasets and auxiliary data over the Northern Hemisphere from 2002 to 2011. The fused snow-depth product was verified at five well-known snow observation sites. The R2 of Sodankylä, Old Aspen, and Reynolds Mountains East were 0.88, 0.69, and 0.63, respectively. At the Swamp Angel Study Plot and Weissfluhjoch observation sites, which have an average snow depth exceeding 200 cm, the fused snow depth did not perform well. The spatial patterns of the average snow depth were analyzed seasonally, and the average snow depths of autumn, winter, and spring were 5.7, 25.8, and 21.5 cm, respectively. In the future, random forest regression will be used to produce a long time series of a fused snow depth dataset over the Northern Hemisphere or other specific regions.

Evaluating the role of soil physical properties on simulated land-atmosphere interactions over South Africa using coupled atmosphere-hydrological modeling

2021 ◽  
Author(s):  
Zhenyu Zhang ◽  
Patrick Laux ◽  
Joël Arnault ◽  
Jianhui Wei ◽  
Jussi Baade ◽  
...  
Keyword(s):  
South Africa ◽  
Physical Properties ◽  
Land Degradation ◽  
Land Surface ◽  
Soil Physical Properties ◽  
Near Surface ◽  
Soil Database ◽  
Global Soil ◽  
The Impact

<p>Land degradation with its direct impact on vegetation, surface soil layers and land surface albedo, has great relevance with the climate system. Assessing the climatic and ecological effects induced by land degradation requires a precise understanding of the interaction between the land surface and atmosphere. In coupled land-atmosphere modeling, the low boundary conditions impact the thermal and hydraulic exchanges at the land surface, therefore regulates the overlying atmosphere by land-atmosphere feedback processes. However, those land-atmosphere interactions are not convincingly represented in coupled land-atmosphere modeling applications. It is partly due to an approximate representation of hydrological processes in land surface modeling. Another source of uncertainties relates to the generalization of soil physical properties in the modeling system. This study focuses on the role of the prescribed physical properties of soil in high-resolution land surface-atmosphere simulations over South Africa. The model used here is the hydrologically-enhanced Weather Research and Forecasting (WRF-Hydro) model. Four commonly used global soil datasets obtained from UN Food and Agriculture Organization (FAO) soil database, Harmonized World Soil Database (HWSD), Global Soil Dataset for Earth System Model (GSDE), and SoilGrids dataset, are incorporated within the WRF-Hydro experiments for investigating the impact of soil information on land-atmosphere interactions. The simulation results of near-surface temperature, skin temperature, and surface energy fluxes are presented and compared to observational-based reference dataset. It is found that simulated soil moisture is largely influenced by soil texture features, which affects its feedback to the atmosphere.</p>

scholarly journals A Study of Desertification Using Remote Sensing Techniques in Basra Governorate, South Iraq

2021 ◽  
pp. 912-926
Author(s):  
Fadel Abbas Zwain ◽  
Thair Thamer Al-Samarrai ◽  
Younus I. Al-Saady
Keyword(s):  
Remote Sensing ◽  
Land Degradation ◽  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Arid Zone ◽  
Sand Dunes ◽  
Risk Index ◽  
Anthropogenic Factors ◽  
Landsat Images

Iraq territory as a whole and south of Iraq in particular encountered rapid desertification and signs of severe land degradation in the last decades. Both natural and anthropogenic factors are responsible for the extent of desertification. Remote sensing data and image analysis tools were employed to identify, detect, and monitor desertification in Basra governorate. Different remote sensing indicators and image indices were applied in order to better identify the desertification development in the study area, including the Normalized difference vegetation index (NDVI), Normalized Difference Water Index (NDWI), Salinity index (SI), Top Soil Grain Size Index (GSI) , Land Surface Temperature (LST) , Land Surface Soil Moisture (LSM), and Land Degradation Risk Index (LDI) which was used for the assessment of degradation severity .Three Landsat images, acquired in 1973, 1993, and 2013, were used to evaluate the potential of using remote sensing analysis in desertification monitoring. The approach applied in this study for evaluating this phenomenon was proven to be an effective tool for the recognition of areas at risk of desertification. The results indicated that the arid zone of Basra governorate encounters substantial changes in the environment, such as decreasing surface water, degradation of agricultural lands (as palm orchards and crops), and deterioration of marshlands. Additional changes include increased salinization with the creeping of sand dunes to agricultural areas, as well as the impacts of oil fields and other facilities.

International Activities Related to Dryland Degradation Assessment and Drought Early Warning

2005 ◽  
Author(s):  
Ashbindu Singh
Keyword(s):  
Land Degradation ◽  
Land Surface ◽  
Food Production ◽  
Agricultural Productivity ◽  
Economic Productivity ◽  
Adequate Diet ◽  
The World ◽  
Sub Saharan ◽  
Drought Early Warning ◽  
Land Degradation And Desertification

Land degradation usually occurs on drylands (arid, semiarid, and dry subhumid areas). According to the United Nations Convention to Combat Desertification held in Paris in 1994 (UNCCD, 1999), drylands are defined as those lands (other than polar and subpolar regions) where the ratio of annual precipitation to potential evapotranspiration falls within the range of 0.05–0.65. Land degradation causes reduction in the biological or economic productivity of those lands that may support cropland, rangelands, forest, and woodlands. Land degradation threatens culturally unique agropastoral and silvopastoral farming systems and nomadic and transhumance systems. The consequences of land degradation are widespread poverty, hunger, migration, and creation of a potential cycle of debt for the affected populations. Historical awareness of the land degradation was cited, mainly at the local and regional scales, by Plato in the 4th century B.C in the Mediterranean region, and in Mesopotamia and China (WRI, 2001). The occurrence of the “dust bowl” in the United States during the 1930s affected farms and agricultural productivity, and several famines and mass migrations, especially in Africa during the 1970s, were important landmarks of land degradation in the 20th century. It is estimated that more than 33% of the earth’s land surface and 2.6 billion people are affected by land degradation and desertification in more than 100 countries. About 73% of rangelands in dryland areas and 47% of marginal rain-fed croplands, together with a significant percentage of irrigated croplands, are currently degraded (WRI, 2001). In sub-Saharan Africa, land degradation is widespread (20–50% of the land) and affects some 200 million people. This region experiences poverty and frequent droughts on a scale not known anywhere else in the world. Land degradation is also severe and widespread in Asia, Latin America, as well as other regions of the globe. Continuous land degradation is accelerating the loss of agricultural productivity and food production in the world. Over the next 50 years, food production needs to triple in order to provide a nutritionally adequate diet for the world’s growing population. This will be difficult to achieve even under favorable circumstances.

scholarly journals An Approach for Downscaling SMAP Soil Moisture by Combining Sentinel-1 SAR and MODIS Data

2019 ◽  
Vol 11 (23) ◽  
pp. 2736 ◽  
Author(s):  
Jueying Bai ◽  
Qian Cui ◽  
Wen Zhang ◽  
Lingkui Meng
Keyword(s):  
Soil Moisture ◽  
Vegetation Cover ◽  
Land Surface ◽  
Feature Space ◽  
Entire Study ◽  
Vegetation Indexes ◽  
Input Variables ◽  
Entire Study Area ◽  
Infrared Data

A method is proposed for the production of downscaled soil moisture active passive (SMAP) soil moisture (SM) data by combining optical/infrared data with synthetic aperture radar (SAR) data based on the random forest (RF) model. The method leverages the sensitivity of active microwaves to surface SM and the triangle/trapezium feature space among vegetation indexes (VIs), land surface temperature (LST), and SM. First, five RF architectures (RF1–RF5) were trained and tested at 9 km. Second, a comparison was performed for RF1–RF5, and were evaluated against in situ SM measurements. Third, two SMAP-Sentinel active–passive SM products were compared at 3 km and 1 km using in situ SM measurements. Fourth, the RF5 model simulations were compared with the SMAP L2_SM_SP product based on the optional algorithm at 3 km and 1 km resolutions. The results showed that the downscaled SM based on the synergistic use of optical/infrared data and the backscatter at vertical–vertical (VV) polarization was feasible in semi-arid areas with relatively low vegetation cover. The RF5 model with backscatter and more parameters from optical/infrared data performed best among the five RF models and was satisfactory at both 3 km and 1 km. Compared with L2_SM_SP, RF5 was more superior at 1 km. The input variables in decreasing order of importance were backscatter, LST, VIs, and topographic factors over the entire study area. The low vegetation cover conditions probably amplified the importance of the backscatter and LST. A sufficient number of VIs can enhance the adaptability of RF models to different vegetation conditions.

scholarly journals Reconstruction of MODIS Land Surface Temperature Products Based on Multi-Temporal Information

2018 ◽  
Vol 10 (7) ◽  
pp. 1112 ◽  
Author(s):  
Jian Kang ◽  
Junlei Tan ◽  
Rui Jin ◽  
Xin Li ◽  
Yang Zhang
Keyword(s):  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Vegetation Index ◽  
Total Error ◽  
Predictor Variables ◽  
Multiple Time ◽  
Modeling Error ◽  
Multi Temporal ◽  
Reconstructed Data

Land surface temperature (LST) products derived from the moderate resolution imaging spectroradiometer (MODIS) sensor are one of the most important data sources used to research land surface energy and water balance at regional and global scales. However, MODIS data are severely contaminated by cloud cover, which limits the applications of LST products. In this paper, based on the spatio-temporal autocorrelation of land surface variables, a reconstruction algorithm depending on the correlations between spatial pixels in multiple time phases from available MODIS LST data is developed to reconstruct clear-sky LST values for missing pixels. Considering the impacts of correlation and bias between predictors and reconstructed data on the modeling error, the known data in the reconstructed time phase are combined with the data temporally nearest to them as predictor variables to establish their temporal relationships with the reconstructed data. The reconstructed results are validated by a series of evaluation indices. The average correlation coefficient between the reconstructed results and ground-based observations is 0.87, showing high temporal change accuracy. The difference in Moran’s I, representing spatial structure characteristics between the known and reconstructed data, is 0.03 on average, indicating a slight loss of spatial accuracy. The average reconstruction rate is approximately 87.0%. The modeling error, as part of the reconstruction error, is only 1.40 K on average and accounts for 5.0% of the total error. If the product and modeling errors are removed, the residual error represents approximately 3.5 K and 5.6 K of the annual mean difference between the cloudy and cloudless LST at night and during the day, respectively. In addition, different reconstruction cases are demonstrated using various predictor data, including many combinations of multi-temporal MODIS LST data, the microwave brightness temperature, and the combination of the normalized difference vegetation index and terrain data. Comparisons among cases show that the known MODIS LST data are more reliable as predictor variables and that the data combination advocated in this paper is optimal.

scholarly journals A Soil Moisture Spatial and Temporal Resolution Improving Algorithm Based on Multi-Source Remote Sensing Data and GRNN Model

2020 ◽  
Vol 12 (3) ◽  
pp. 455 ◽  
Author(s):  
Yaokui Cui ◽  
Xi Chen ◽  
Wentao Xiong ◽  
Lian He ◽  
Feng Lv ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Soil Moisture ◽  
Temporal Resolution ◽  
Land Surface ◽  
Regional Scale ◽  
Remote Sensing Data ◽  
The Tibetan Plateau ◽  
Sensing Data ◽  
Spatio Temporal ◽  
Input Variables

Surface soil moisture (SM) plays an essential role in the water and energy balance between the land surface and the atmosphere. Low spatio-temporal resolution, about 25–40 km and 2–3 days, of the commonly used global microwave SM products limits their application at regional scales. In this study, we developed an algorithm to improve the SM spatio-temporal resolution using multi-source remote sensing data and a machine-learning model named the General Regression Neural Network (GRNN). First, six high spatial resolution input variables, including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), albedo, Digital Elevation Model (DEM), Longitude (Lon) and Latitude (Lat), were selected and gap-filled to obtain high spatio-temporal resolution inputs. Then, the GRNN was trained at a low spatio-temporal resolution to obtain the relationship between SM and input variables. Finally, the trained GRNN was driven by the high spatio-temporal resolution input variables to obtain high spatio-temporal resolution SM. We used the Fengyun-3B (FY-3B) SM over the Tibetan Plateau (TP) to test the algorithm. The results show that the algorithm could successfully improve the spatio-temporal resolution of FY-3B SM from 0.25° and 2–3 days to 0.05° and 1-day over the TP. The improved SM is consistent with the original product in terms of both spatial distribution and temporal variation. The high spatio-temporal resolution SM allows a better understanding of the diurnal and seasonal variations of SM at the regional scale, consequently enhancing ecological and hydrological applications, especially under climate change.

South African Land Degradation Monitor (SALDI) – A German – South African SPACES collaboration to advance land degradation assessments

2020 ◽  
Author(s):  
Jussi Baade ◽  
Andreas Kaiser ◽  
Keyword(s):  
South Africa ◽  
South African ◽  
Land Degradation ◽  
Land Surface ◽  
Soil Degradation ◽  
Assessment Tools ◽  
Automated System ◽  
Observation Data ◽  
Clean Water ◽  
Cooperative Research

<p>South Africa is greatly affected by land degradation, partly due to the high variability of its climatic conditions, the strong population growth and resulting economic demands. Thus reaching a number of SDGs, like achieving food security (#2), access to clean water (#6), and the sustainable use of terrestrial (#15) and marine (#14) resources represents a clear challenge under the present global change pressures. Land degradation has been linked in South Africa to the terms veld degradation and soil degradation and has been addressed by numerous measures. But there is still uncertainty on the extent of human induced land degradation as compared to periodic climate induced land surface property changes.</p><p>In cooperation with South African institutions and stakeholders (ARC-ISCW, SAEON, SANParks, SANSA, Stellenbosch University and University of the Free State, Equispectives Research and Consulting Services, Nuwejaars Wetlands SMA), the overarching goal of SALDi is to implement novel, adaptive, and sustainable tools for assessing land degradation in multi-use landscapes in South Africa. Building upon the state of the art in land degradation assessments, the project aims to advance current methodologies for multi-use landscapes by innovatively incorporating inter-annual and seasonal variability in a spatially explicit approach. SALDi takes advantage of the emerging availability of high spatio-temporal resolution Earth observation data (e.g. Copernicus Sentinels, DLR TanDEM-X, NASA/USGS Landsat program), growing sources of in-situ data and advancements in modelling approaches. Particularly, SALDi aims to:</p><ol><li>i) develop an automated system for high temporal frequency (bi-weekly) and spatial resolution (10 to 30 m) change detection monitoring of ecosystem service dynamics,</li> <li>ii) develop, adapt and apply a Regional Earth System Model (RESM) to South Africa and investigate the feedbacks between land surface properties and the regional climate,</li> </ol><p>iii)    advance current soil degradation process assessment tools for soil erosion, as this process represents an intrinsic limiting factor for biomass production and other regulating, supporting and provisioning ecosystem services, like providing clean water.</p><p>The aim of this presentation is to introduce this new cooperative research project to the EGU Community and to seek new opportunities for collaboration.</p>

scholarly journals A Spatially Distributed Groundwater Metric for Describing Hydrologic Changes in a Regional Population of Wetlands North of Tampa Bay, Florida, from 1990 to 2015

2021 ◽  
Author(s):  
Geoffrey Fouad ◽  
Terrie M. Lee
Keyword(s):  
Land Surface ◽  
Flow Direction ◽  
Critical Role ◽  
Flow Equation ◽  
Wet Season ◽  
Drainage Basins ◽  
Spatially Distributed ◽  
Groundwater Condition ◽  
Regional Population ◽  
Condition Metric

Abstract A groundwater condition metric is presented and used to evaluate hydrologic changes in a regional population of wetlands in and around municipal well fields with large groundwater withdrawals. The approach compares a 26-year, monthly time series of groundwater potentiometric surfaces to light detection and ranging (LiDAR) land-surface elevations at 10,516 wetlands in a 1505-square-kilometer area. Elevation differences between the potentiometric surface and wetland land surface provide a flow direction (upward or downward) and a proxy for vertical hydraulic head difference in Darcy’s groundwater flow equation. The resulting metric quantifies the groundwater condition at a wetland through time as the potential for groundwater to discharge upward into a wetland or for water in a wetland to leak downward to recharge the underlying aquifer. The potential for wetland leakage across the regional wetland population decreased by 33% in the 13 years after cutbacks in groundwater withdrawals (2003-2015) compared to years before cutbacks (1990-2002). Inside well field properties, wetland leakage potential decreased by 24%. In the wet season month of September, wetlands with the potential to receive groundwater discharge increased to 21.6% of the regional population after cutbacks compared to 13.3% before cutbacks. When mapped across regional drainage basins, discharging wetlands formed spatial connections suggesting they play a critical role in generating streamflow.

scholarly journals Degradation of net primary production in a semiarid rangeland

2016 ◽  
Vol 13 (16) ◽  
pp. 4721-4734 ◽  
Author(s):  
Hasan Jackson ◽  
Stephen D. Prince
Keyword(s):  
Primary Production ◽  
Land Degradation ◽  
Land Surface ◽  
Net Primary Production ◽  
Small Areas ◽  
Small Fields ◽  
The Difference ◽  
Vegetation Models ◽  
Annual Reduction ◽  
Global Vegetation

Abstract. Anthropogenic land degradation affects many biogeophysical processes, including reductions of net primary production (NPP). Degradation occurs at scales from small fields to continental and global. While measurement and monitoring of NPP in small areas is routine in some studies, for scales larger than 1 km2, and certainly global, there is no regular monitoring and certainly no attempt to measure degradation. Quantitative and repeatable techniques to assess the extent of deleterious effects and monitor changes are needed to evaluate its effects on, for example, economic yields of primary products such as crops, lumber, and forage, and as a measure of land surface properties which are currently missing from dynamic global vegetation models, assessments of carbon sequestration, and land surface models of heat, water, and carbon exchanges. This study employed the local NPP scaling (LNS) approach to identify patterns of anthropogenic degradation of NPP in the Burdekin Dry Tropics (BDT) region of Queensland, Australia, from 2000 to 2013. The method starts with land classification based on the environmental factors presumed to control (NPP) to group pixels having similar potential NPP. Then, satellite remotely sensing data were used to compare actual NPP with its potential. The difference in units of mass of carbon and percentage loss were the measure of degradation. The entire BDT (7.45  ×  106 km2) was investigated at a spatial resolution of 250  ×  250 m. The average annual reduction in NPP due to anthropogenic land degradation in the entire BDT was −2.14 MgC m−2 yr−1, or 17 % of the non-degraded potential, and the total reduction was −214 MgC yr−1. Extreme average annual losses of 524.8 gC m−2 yr−1 were detected. Approximately 20 % of the BDT was classified as “degraded”. Varying severities and rates of degradation were found among the river basins, of which the Belyando and Suttor were highest. Interannual, negative trends in reductions of NPP occurred in 7 % of the entire region, indicating ongoing degradation. There was evidence of areas that were in a permanently degraded condition. The findings provide strong evidence and quantitative data for reductions in NPP related to anthropogenic land degradation in the BDT.

Sign in / Sign up

Export Citation Format

Share Document