Salinity Index Research Articles

Application of GIS-based machine learning algorithms for prediction of irrigational groundwater quality indices

Agriculture is considered one of the primary elements for socioeconomic stability in most parts of Sudan. Consequently, the irrigation water should be properly managed to achieve sustainable crop yield and soil fertility. This research aims to predict the irrigation indices of sodium adsorption ratio (SAR), sodium percentage (Na%), permeability index (PI), and potential salinity (PS) using innovative machine learning (ML) techniques, including K-nearest neighbor (KNN), random forest (RF), support vector regression (SVR), and Gaussian process regression (GPR). Thirty-seven groundwater samples are collected and analyzed for twelve physiochemical parameters (TDS, pH, EC, TH, Ca+2, Mg+2, Na+, HCO3−, Cl, SO4−2, and NO3−) to assess the hydrochemical characteristics of groundwater and its suitability for irrigation purposes. The primary investigation indicated that the samples are dominated by Ca-Mg-HCO3 and Na-HCO3 water types resulted from groundwater recharge and ion exchange reactions. The observed irrigation indices of SAR, Na%, PI, and PS showed average values of 7, 42.5%, 64.7%, and 0.5, respectively. The ML modeling is based on the ion’s concentration as input and the observed values of the indices as output. The data is divided into two sets for training (70%) and validation (30%), and the models are validated using a 10-fold cross-validation technique. The models are tested with three statistical criteria, including mean square error (MSE), root means square error (RMSE), and correlation coefficient (R2). The SVR algorithm showed the best performance in predicting the irrigation indices, with the lowest RMSE value of 1.45 for SAR. The RMSE values for the other indices, Na%, PI, and PS, were 6.70, 7.10, and 0.55, respectively. The models were applied to digital predictive data in the Nile River area of Khartoum state, and the uncertainty of the maps was estimated by running the models 10 times iteratively. The standard deviation maps were generated to assess the model’s sensitivity to the data, and the uncertainty of the model can be used to identify areas where a denser sampling is needed to improve the accuracy of the irrigation indices estimates.

Soil Salinity Estimation for South Kazakhstan Based on SAR Sentinel-1 and Landsat-8,9 OLI Data with Machine Learning Models

Climate change, uneven distribution of water resources and anthropogenic impact have led to salinization and land degradation in the southern regions of Kazakhstan. Identification of saline lands and their mapping is a laborious process associated with a complex of ground measurements. Data from remote sensing are widely used to solve this problem. In this paper, the problem of assessing the salinity of the lands of the South Kazakhstan region using remote sensing data is considered. The aim of the study is to analyze the applicability of machine learning methods to assess the salinity of agricultural lands in southern Kazakhstan based on remote sensing. The authors present a salinity dataset obtained from field studies and containing more than 200 laboratory measurements of soil salinity. Moreover, the authors describe the results of applying several regression reconstruction algorithms (XGBoost, LightGBM, random forest, Support vector machines, Elastic net, etc.), where synthetic aperture radar (SAR) data from the Sentinel-1 satellite and optical data in the form of spectral salinity indices are used as input data. The obtained results show that, in general, these input data can be used to estimate salinity of the wetted arable land. XGBoost regressor (R2 = 0.282) showed the best results. Supplementing the radar data with the values of salinity spectral index improves the result significantly (R2 = 0.356). For the local datasets, the best result shown by the model is R2 = 0.473 (SAR) and R2 = 0.654 (SAR with spectral indexes), respectively. The study also revealed a number of problems that justify the need for a broader range of ground surveys and consideration of multi-year factors affecting soil salinity. Key results of the article: (i) a set of salinity data for different geographical zones of southern Kazakhstan is presented for the first time; (ii) a method is proposed for determining soil salinity on the basis of synthetic aperture radar supplemented with optical data, and this resulted in the improved prediction of the results for the region under consideration; (iii) a comparison of several types of machine learning models was made and it was found that boosted models give, on average, the best prediction result; (iv) a method for optimizing the number of model input parameters using explainable machine learning is proposed; (v) it is shown that the results obtained in this work are in better agreement with ground-based measurements of electrical conductivity than the results of the previously proposed global model.

Spatial Mapping of Soil Salinity Using Machine Learning and Remote Sensing in Kot Addu, Pakistan

The accumulation of salt through natural causes and human artifice, such as saline inundation or mineral weathering, is marked as salinization, but the hindrance toward spatial mapping of soil salinity has somewhat remained a consistent riddle despite decades of efforts. The purpose of the current study is the spatial mapping of soil salinity in Kot Addu (situated in the south of the Punjab province, Pakistan) using Landsat 8 data in five advanced machine learning regression models, i.e., Random Forest Regressor, AdaBoost Regressor, Decision Tree Regressor, Partial Least Squares Regression and Ridge Regressor. For this purpose, spectral data were obtained between 20 and 27 of January 2017 and a field survey was carried out to gather a total of fifty-five soil samples. To evaluate and compare the model’s performances, the coefficient of determination (R2), Mean Squared Error (MSE), Mean Absolute Error (MAE) and the Root-Mean-Squared Error (RMSE) were used. Spectral data of band values, salinity indices and vegetation indices were employed to study the salinity of soil. The results revealed that the Random Forest Regressor outperformed the other models in terms of prediction, achieving an R2 of 0.94, MAE of 1.42 dS/m, MSE of 3.58 dS/m and RMSE of 1.89 dS/m when using the Differential Vegetation Index (DVI). Alternatively, when using the Soil Adjusted Vegetation Index (SAVI), the Random Forest Regressor achieved an R2 of 0.93, MAE of 1.46 dS/m, MSE of 3.90 dS/m and RMSE of 1.97 dS/m. Hence, remote sensing technology with machine learning models is an efficient method for the assessment of soil salinity at local scales. This study will contribute to mitigating osmotic stress and minimizing the risk of soil erosion by providing early warnings regarding soil salinity. Additionally, it will assist agriculture officers in estimating soil salinity levels within a shorter time frame and at a reduced cost, enabling effective resource allocation.

Developing a satellite-based combined land degradation index for monitoring environmental change: A case study in Tana-Beles watershed, Upper Blue Nile, Ethiopia

Land degradation is one of the most pressing environmental challenges due to its effect on the people and ecosystem. Early detection of land degradation could help to avoid further deterioration and work on reversing the trend. This would require an integrated approach combining indicators such as vegetation condition, soil health (i.e., soil salinity), and soil exposure (i.e., albedo) to characterize land degradation comprehensively. Therefore, this study aims at developing a satellite image-based combined land degradation index to monitor the spatial extent of land degradation in the Upper Blue Nile Basin, Ethiopia. In addition, the study also evaluates the environmental change associated with land degradation across the Tana-Beles watershed. The combined land degradation index (CLDI) was developed by integrating multiple indicators, including normalized vegetation Index (NDVI), salinity index (SI), and albedo, for two periods spanning between 1990 and 2000 (1990s) and 2010 to 2020 (2010s). The individual indicators were combined with Principal Component Analysis (PCA) by assigning weights to the individual indicators. The analysis indicated that, in the 2010s, the vegetation condition deteriorated over 98.5% of the study area, while soil salinity and albedo increased by 82% and 97% in the 1990s, respectively. The combined land degradation index developed with the PCA indicated in the 2020s a fraction of the study area ∼2% is extremely degraded, while 18%, 43%, 27%, and 10% of the site is strongly, moderately, slightly, and not degraded, respectively. Monitoring land degradation is important for countries like Ethiopia, where most of the county are occupied by semi-arid and arid climate zones.

Groundwater Hydrogeochemistry Impacted by Industrial Activities in Ain Sukhna Industrial Area, North-Western Part of the Gulf of Suez, Egypt

Economic development and human life depend on groundwater resources in arid regions around the world. To define water quality in the Northwest Gulf of Suez, its elements, geogenic and anthropogenic sources, and suitability for various purposes, ten groundwater samples were collected and analyzed from wells tapping Quaternary and Tertiary aquifers. Average ion distribution was in the following order: Na+ > Mg2+ > Ca2+ > K+ and Cl− > SO42− > HCO3−. Two water types with hydrochemical Ca-Mg-Cl-SO4 facies accounted for 30% of samples due to reverse ion exchange, while Na-K-Cl-SO4 accounted for 70% of samples due to evaporation. Cd (0–0.042 mg/L) and Pb (0–0.222 mg/L) from industrial applications in the study area exceeded the acceptable values in drinking water (>0.003 and 0.01 mg/L, respectively). Heavy metals and ionic value enrichment are due to weathering, precipitation/evaporation, ion exchange, and anthropogenic activities. Most ions in groundwater are higher than the acceptable limits prescribed for drinking water at all sites. Most groundwater in the investigated area is inappropriate for irrigation based on total salinity and MH index. High-salinity-tolerant plants and vegetables can be utilized according to the USSLS diagram. All groundwater samples have improper effects of incrustation and corrosion. Proper management actions are recommended to ameliorate the groundwater quality.

Partial least-squares regression for soil salinity mapping in Bangladesh

Estimating the salinity of the soil along the coast of south-western Bangladesh is the focus of this study. Thirteen soil salinity indicators were computed using the Landsat OLI images, and 241 soil salinity samples were gathered from secondary sources. In this research, partial least-squares regression was used to estimate soil salinity. Soil salinity zones were then divided into five classes based on Jenks natural breaks. There is a strong relationship between soil salinity and several indices, including B2 (Blue band), B5 (Near-Infrared band), SI_1 (Salinity index 1), and SI_2 (Salinity index 2). The correlation between B2 and soil salinity is particularly high, hovering around 0.92. The majority of other factors, however, have a negative or barely positive correlation of −0.260 to 0.032. Very high and high levels of salinity are estimated to cover 29.02% and 13.45% of the study area, respectively, based on the soil salinity map. Finally, cross-validation has been used to see how well the model works to predict soil salinity for a specified weight. Iteration has been done three times in order to assess the model's performance on various subsets of data and produce a more accurate prediction. In the third iteration, PRESS, RSS, and Q2cum values were 1.844826, 3.354687, and 0.9705131, correspondingly, which indicates a higher predictive accuracy. The findings of the study will be useful as a tool for policymakers in the south-western coastal area of Bangladesh who are responsible for integrated coastal zone management.

Applying Geophysical and Hydrogeochemical Methods to Evaluate Groundwater Potential and Quality in Middle Egypt

The El-Minia district is a location of interest for future urban development. Using hydrochemistry and electrical resistivity studies, this work aimed to evaluate the groundwater potentiality and it’s suitable for various uses. The groundwater potential in the study area was evaluated based on 24 VESs (vertical electrical soundings), and its quality was determined based on the analyses of 57 groundwater samples. EC (salinity index), Na% (salt hazard), SAR (ratio of sodium adsorption), chloride risks, SSP (soluble sodium percentage), MH (magnesium hazard), and other indicators were used to determine whether the collected water samples were suitable for irrigation. Four layers in the study area are mentioned in the geoelectrical cross-sections that have been constructed. The first is made up of silt and clay from the Nile River, while the second is made up of sandy clay, which has a resistivity range of 15 to 32 Ohm.m and a range thickness of 2 to 68 m. Dry limestone makes up the third layer; its resistivity ranges from 1222 to 3000 Ohm.m and its thickness varies between 75 and 95 m. The Eocene aquifer in the research area is represented by the final layer, which has a thickness of more than 250 m and resistivity values that range from 602 to 860 Ohm.m. Most groundwater samples that were collected are safe for drinking; however, none of them are fit for home usage because of their extreme hardness. According to the SAR and US diagram, RSC, KR, and PI, most groundwater samples from the Pleistocene and Eocene aquifers are fit for irrigation.

Inversion Model of Salt Content in Alfalfa-Covered Soil Based on a Combination of UAV Spectral and Texture Information

This study aimed to investigate how the combination of texture information and spectral index affects the accuracy of the soil salinity inversion model. Taking the Bianwan Farm in Jiuquan City, Gansu Province, China as the research area, the multi-spectral data and soil salinity data at 0–15 cm, 15–30 cm and 30–50 cm depths in the sampling area under alfalfa coverage were collected, and spectral reflectance and texture features were obtained from a multispectral image. Moreover, the red-edge band was introduced to improve the spectral index, and gray correlation analysis was utilized to screen sensitive features. Five types of alfalfa-covered soil salinity machine learning inversion models based on random forest (RF) and extreme learning machine (ELM) algorithms were constructed, using the salinity index (SIs), vegetation index (VIs), salinity index + vegetation index (SIs + VIs), vegetation index + texture feature (VIs + TFs), and vegetation index + texture index (VIs + TIs). The determination coefficient R2, root-mean-square error (RMSE) and mean absolute error (MAE) were used to evaluate each model’s performance. The results show that the VIs model is more accurate than the SIs and SIs +VIs models. Combining texture information with VIs improves the inversion accuracy, and the VIs + TIs model has the best inversion effect. From the perspective of inversion depth, the inversion effect for 0–15 cm soil salinity was significantly better than that for other depths, and was the best inversion depth under alfalfa cover. The average R2 of the RF model was 10% higher than that of the ELM. The RF algorithm has high inversion accuracy and stability and performs better than ELM. These findings can serve as a theoretical basis for the efficient inversion of soil salinity and management of saline–alkali lands.

Estuarine salinity extremes: Using the Coastal Salinity Index to quantify the role of droughts, floods, hurricanes, and freshwater flow alteration

In the face of accelerating climate change, advancing understanding of how extreme climatic events influence estuarine salinities can help to inform resource management. Extreme salinities driven by droughts, hurricanes, floods, and freshwater flow alterations can lead to ecological transformations in estuarine ecosystems. Here, we applied the Coastal Salinity Index (CSI; Conrads and Darby 2017) to 22 years (1998–2020) of salinity data in a Louisiana estuary (Barataria Estuary, USA) to elucidate the impacts of extreme events on estuarine salinities. The CSI is an index to quantify salinity patterns at a specific location through long-term averages and deviations from historical average conditions. We calculated and compared CSI values for four stations distributed along an estuarine salinity gradient. We identified 10 events between 1998 and 2020 that produced extreme salinities, including two droughts, four hurricanes, three floods, and one freshwater diversion. The droughts of 2000 and 2006 caused surface water salinities to increase substantially throughout the estuary. The effects of hurricanes were highly variable, with some storms leading to elevated salinities throughout the entire estuary (e.g., Hurricanes Katrina and Rita in 2005), whereas other storms led to elevated salinities for some but not all stations (e.g., Hurricanes Gustav and Ike in 2008 or Hurricane Isaac in 2012). The opening of a freshwater river diversion in 2010 contributed to fresher conditions throughout the estuary and appeared to reduce or eliminate the increases in salinity that normally occur during the summer, although these effects were short-lived. Mississippi River floods in 2008, 2011, and 2019 reduced salinities throughout the estuary, but the effects were most pronounced in the lower estuary compared to the upper estuary. Collectively, our results advance understanding of the influence of extreme events on estuarine salinity regimes. Our analyses also highlight the value of the CSI for identifying periods with extreme salinities (i.e., extreme high or low salinities) via calculations that place salinity levels within and across estuaries within a historical context.

Evaluating the spatiotemporal variations of soil salinity in Sirjan Playa, Iran using Sentinel-2A and Landsat-8 OLI imagery

The creation of large-scale deserts is a consequence of soil salinization, a major land degradation phenomenon that also disrupts ecological equilibrium. Saline lands can be evaluated, mapped, and monitored in different world regions using satellite imaging and remote sensing techniques. In order to assess the ability of Landsat-8 and Sentinel-2A imagery for monitoring the spatiotemporal variations of electrical conductivity (EC) and to determine the importance of salinity indices for prediction in two seasons (summer and winter) using the systematic sampling method, from surface depth (0––20 cm), 90 soil samples were taken of marginal lands of Sirjan Playa, southeast of Iran. Satellite images for two seasons were acquired close to the sampling time to obtain the soil salinity indices. Four machine-learning algorithms, namely artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM), were applied to estimate the spatiotemporal changes in soil salinity. Results confirmed that the ANN model developed by the Sentinel-2A image had the highest performance (R2 = 0.77, RMSE = 16.1, NRMSE = 27.1) to predict ECe in the winter season. Furthermore, RF presents the lowest error for prediction ECe during the summer, independent type of satellite data used. Additionally, in virtually all of the analyzed models, the Sentinel-2A data produced lower RMSE and NRMSE values than the Landsat-8 data throughout the two seasons. Results also confirmed that among the soil salinity indices, the Vegetation Soil Salinity Index (VSSI) was identified as the most effective predictor. Overall, this study demonstrates the potential of satellite imaging and machine learning algorithms for monitoring and predicting soil salinity, which can contribute to the sustainable management of marginal lands in arid and semi-arid regions. The findings also highlight the importance of selecting appropriate satellite data and salinity indices for accurate and reliable predictions.

A drought index based on groundwater quantity and quality: Application of multivariate copula analysis

In this paper, a new Groundwater Quantity-Quality-based Drought Index (GQQI) is developed based on multivariate Copula analysis of groundwater quantity and quality indicators. For evaluating the developed index, its temporal and spatial distribution is studied and compared to those of some other indices, such as Standardized Salinity Index (SSI), Standardized Groundwater Index (SGI), and Standardized Water level Index (SWI). The proposed index is applied for the temporal and spatial evaluation of the quantity and quality of groundwater in theLake Urmia basin, having 1084 piezometric and 935 groundwater quality monitoring wells. For a more comprehensive analysis of drought, 24 marginal and 26 joint probability distribution functions are driven. Based on the results, the developed GQQI is correlated with drought indices of SSI, SGI, and SWI by 88%, 86%, and 61%, respectively. Moreover, the values of the developed drought index indicates the occurrence of more severe droughts, compared to those detected by other drought indices. This can be resulted from considering the combined effects of groundwater quantity and quality using the proposed index. In addition, the multivariate GQQI can spatially and temporally represent the drought severity over the basin, and identify severe and extreme drought conditions better than other univariate drought indices.

Detecting Long-Term Series Eco-Environmental Quality Changes and Driving Factors Using the Remote Sensing Ecological Index with Salinity Adaptability (RSEISI): A Case Study in the Tarim River Basin, China

Ecological challenges resulting from soil salinization in the Tarim River Basin (TRB), exacerbated by climate change and human activities, have emphasized the need for a quick and accurate assessment of regional ecological environmental quality (EEQ) and driving mechanisms. To address this issue, this study has developed a remote-sensing ecological index with salinity adaptability (RSEISI) for EEQ assessment in the Tarim River Basin by integrating the comprehensive salinity index (CSI) into the remote-sensing ecological index (RSEI). The RSEISI enhances the sensitivity of soil salinity and characterizes the surface features of arid regions, thus expanding the applicability. Then, we used time-series analysis methods and a geodetector to quantify the spatial temporal trends and driving factors of EEQ in the TRB from 2000 to 2022. The results show that the RSEISI with salinity adaptation effectively monitors the EEQ of the TRB. The EEQ of the TRB displayed the situation of oasis expansion, desert deterioration, and glacier melting, and the multiyear average EEQ grades were dominated by medium and poor grades in desert and saline areas, while medium, good, and excellent grades were concentrated in oasis and mountainous areas. Looking at the trend of change in conjunction with land-use types, the EEQ of the TRB showed a mild degradation trend mainly in unused land, followed by a mild improvement trend in cropland and grassland. The Hurst index indicated that the EEQ of most areas of the TRB will improve in the future. Soil type, land use, precipitation, and temperature were considered to be key factors affecting the EEQ across the TRB, and changes in the EEQ were found to be the interaction of multiple factors. This study may provide innovative concepts and methodologies, scientific and technological support for ecological management, and green development models in the northwest arid zone.

Use of a Dielectric Sensor for Salinity Determination on an Extensive Green Roof Substrate.

The irrigation of extensive green roofs with recycled or saline water could contribute to the conservation of valuable drinking water supplies. In such cases, the continuous monitoring of substrate electrical conductivity (ECsw) is of immense importance for the sustainable growth of the plants growing on the green roof. The present study aimed to estimate the ECsw (pore water EC) of an extensive green roof substrate in lysimeters with the use of the WET-2 dielectric sensor. Half of the 48 lysimeters that simulated extensive green roofs had a substrate depth of 7.5 cm, while the other half had a 15 cm substrate depth. The warm season turfgrass Paspalum vaginatum 'Platinum TE' was established at the lysimeters, and during the summer period, it was irrigated every two days at a rate of 14 mm with NaCl solutions of various electrical conductivities (ECi): (a) 3 dS m-1, (b) 6 dS m-1, and (c) 12 dS m-1, while potable water of 0.3 dS m-1 ECi served as the control. The relation between bulk electrical conductivity, σb, and bulk dielectric permittivity, εb, of the substrate was observed to be linear for all ECi levels up to σb values of 2-2.5 dS m-1. The ECsw was predicted by employing the salinity index method which was modified to be applied to the particular case of a green roof substrate. Knowing the salinity index and organic portion (%, v/v) for a given green roof substrate, we could calculate the ECsw. It was found that the use of the salinity index method predicts reliably the ECsw up to 10-11 dS m-1, while the method overestimates ECsw at very low levels of electrical conductivity.

Assessment of soil salinity by geo-spatial technology in Ballia district of Uttar Pradesh

Soils vary in their characteristics from one place to another place due to interactions of soil forming and processes. Assessment of spatial and temporal variation of characteristics is needed for any mean or use it's crucial to take into account the diverse spatial differences in soil properties, which has long in this context. Geographic information system (GIS) technology has enormous potential in the field of soil's assessment for upgrading soil statistic systems for an accurate and cost-effective means of understanding changes in the landscape. The future agricultural monitoring of the nutritional quality of the soil in diverse regions and villages is crucial. In this paper assessment of spatial variation of soil salinity using GIS techniques around the Ballia District of Uttar Pradesh is presented from the year 1994 to 2019. Normalized Difference Salinity Index (NDSI) was used. It showed increasing trend in salinity from 1994 to 2019 for each block. Using Landsat (TM/OLI) imageries with a 30 m spatial resolution, the spatial distribution of salinity from 1994 to 2019 was determined and low negative NDSI value was observed from - 0.143 to -0.117 in the southeast part of Ballia which can be an important explanation for soil degradation due to increasing soil salinity.

Detection of the Spatial Variability of Soil Salinity East of the Bitter Lake of the Suez Canal, Egypt, as a Basis for Management Zones Using Sentinel-2 Multispectral Imagery

ABSTRACT Soil salinity is one of the more serious problems that cause soil degradation, particularly in semi-arid and arid regions. In agricultural lands, it threatens plant growth and productivity, which requires specific management decisions for various inputs, such as fertilizers. Accurate prediction and mapping of soil salinity have become possible through remote sensing techniques. The focus of this research is to derive soil salinity from spectral indices measured from different bands of sentinel-2 satellite in order to delineate management zones (MZs). Four spectral salinity indices were used for the purpose of this study, using blue, green, red, and NIR bands in different combinations. Exponential regression best describes the relationship between salinity indices and soil electrical conductivity (EC) through groundtruthing. The results indicate that salinity indices 2 () and 4 () (SI2 and SI4) outperformed the other indices and could describe 70% and 71% of the variability in soil EC with prediction models of: and , respectively. The generated models were validated by normalized root mean square error and the d coefficient of agreement. The results of the best-fit models were 16.5% and 0.86 for SI2 and 16.7% and 0.84 for SI4, respectively. The box-and-whiskers diagram proposed that the field can be divided into four soil EC-dependent groups, which are considered MZs to support a variety of management decisions. This study shows that through sentinel-2 multispectral imagery, the spatial variability of soil salinity can be mapped and used as a basis for MZs within the studied region.

A novel method for detecting soil salinity using AVIRIS-NG imaging spectroscopy and ensemble machine learning

Soil salinization is one of the major land degradation processes spread over millions of hectares of global land. Hyperspectral Remote Sensing (HRS) coupled with modern data mining approaches help in real-time and cost-effective assessment or monitoring of salt-affected soils. This study aimed at predicting soil salinity across five sites in India using the Airborne Visible-Infrared Imaging Spectrometer - Next Generation (AVIRIS-NG) data in low to moderately salt-affected cropland soils. We have identified four unique spectral absorption features having sensitivity towards soil salinity through a hybrid feature selection algorithm. Soil electrical conductivity (EC) was estimated using different machine learning (ML) based models such as random forest (RF), gradient boosting machines (GBM), and deep learning (DL). An ensemble of RF and DL models showed the best performance with the coefficient of determination (R2) of 0.89 and 0.55 and normalized root-mean-squared error of 0.15 and 0.16 in training and test datasets, respectively. We also proposed a new hyperspectral soil salinity index using Shannon entropy-based aggregation of selected absorption features. The newly proposed index outperformed other majorly used remote sensing-based salinity indices. It also showed a strong correlation with measured EC (r = 0.68) and ML-predicted soil EC (r = 0.78), both being significant at 1% level of significance. The index was effective in classifying HRS images into six distinct salinity classes. We also assessed the feasibility of applying the proposed salinity index for future hyperspectral missions through the simulation of various spectral-spatial resampling scenarios and estimated the optimal spectral and spatial resolution for salinity prediction. The hyperspectral salinity index can be directly estimated from HRS data without the need for time-consuming and expensive field samplings and used as a proxy to evaluate soil salinity status under field conditions.

A new salinity index for the invertebrate fauna of Australian inland waters

Anthropogenic salinisation of inland waters worldwide causes diverse social, economic and ecological impacts, including shifts in the composition of biological communities. I used published data on occurrence of aquatic invertebrate taxa in relation to salinity to develop a novel Invertebrate-Based Salinity Index (IBSI) suitable for purposes such as indicating the ecological impact of anthropogenic salinisation and charting faunal recovery after salinity mitigation. Testing of the index with data independent of those used in its derivation showed a stronger association with salinity than prior Australian salinity indices based on macroinvertebrates. IBSI is applicable to both running and standing inland waters across Australia, and could be extended to other countries. Potential limitations of IBSI and its underlying salinity tolerance values are discussed, and suggestions are made for future index refinement and testing.

Random Forest Modeling of Soil Properties in Saline Semi-Arid Areas

The problem of salinization/spreading of saline soils is becoming more urgent in many regions of the world, especially in context of climate change. The monitoring of salt-affected soils’ properties is a necessary procedure in land management and irrigation planning and is aimed to obtain high crop harvest and reduce degradation processes. In this work, a machine learning method was applied for modeling of the spatial distribution of topsoil (0–20 cm) properties—in particular: soil organic carbon (SOC), pH, and salt content (dry residue). A random forest (RF) machine learning approach was used in combination with environmental variables to predict soil properties in a semi-arid area (Trans-Ural steppe zone). Soil, salinity, and texture maps; topography attributes; and remote sensing data (RSD) were used as predictors. The coefficient of determination (R2) and the root mean square error (RMSE) were used to estimate the performance of the RF model. The cross-validation result showed that the RF model achieved an R2 of 0.59 and an RMSE of 0.68 for SOM; 0.36 and 0.65, respectively, for soil pH; and 0.78 and 1.21, respectively for dry residue prediction. The SOC content ranged from 0.8 to 2.8%, with an average value of 1.9%; soil pH ranged from 5.9 to 8.4, with an average of 7.2; dry residue varied greatly from 0.04 to 16.8%, with an average value of 1.3%. A variable importance analysis indicated that remote sensing variables (salinity indices and NDVI) were dominant in the spatial prediction of soil parameters. The importance of RSD for evaluating saline soils and their properties is explained by their absorption characteristics/reflectivity in the visible and near-infrared spectra. Solonchak soils are distinguished by a salt crust on the land surface and, as a result, reduced SOC contents and vegetation biomass. However, the change in saline and non-saline soils over a short distance with mosaic structure of soil cover requires high-resolution RSD or aerial images obtained from unmanned aerial vehicle/drones for successful digital mapping of soil parameters. The presented results provide an effective method to estimate soil properties in saline landscapes for further land management/reclamation planning of degraded soils in arid and semi-arid regions.

Remote Sensing Monitoring of Soil Salinity in Weigan River–Kuqa River Delta Oasis Based on Two-Dimensional Feature Space

Soil salinization is a serious resource and ecological problem globally. The Weigan River–Kuqa River Delta Oasis is a key region in the arid and semi-arid regions of China with prominent soil salinization. The saline soils in the oasis are widely distributed over a large area, causing great harm to agricultural development and the environment. Remote sensing monitoring can provide a reference method for the management of regional salinization. We extracted the spectral indices and performed a correlation analysis using soil measurement data and Sentinel-2 remote sensing data. Then, two-dimensional feature space inversion models for soil salinity were constructed based on the preferred spectral indices, namely, the canopy response salinity index (CRSI), composite spectral response index (COSRI), normalized difference water index (NDWI), and green atmospherically resistant vegetation index (GARI). The soil salinity in a typical saline zone in the Weigan River–Kuqa River Delta Oasis was monitored and analyzed. We found that the inversion of the CRSI-COSRI model was optimal (R2 of 0.669), followed by the CRSI-NDWI (0.656) and CRSI-GARI (0.604) models. Therefore, a model based on the CRSI-COSRI feature space can effectively extract the soil salinization information for the study area. This is of great significance to understanding the salinization situation in the Weigan River–Kuqa River Delta Oasis, enriching salinization remote sensing monitoring methods, and solving the soil salinization problem in China.

Quantifying the coal mining impact on the ecological environment of Gobi open-pit mines

Xinjiang is a coal-rich region with many bare rocky and gravelly areas with a delicate and fragile ecology. What is the ecological impact of mining activities? In this study, the Salinity Index (SI-T), New Gravel Land Index (NGLI), and Land Deterioration Index (LD) were used to establish an improved remote sensing ecological index (IRSEI) for the HongShaQuan open-pit coal mine (HSQ). The spatial and temporal evolution of the ecological environment of the HSQ was revealed by IRSEI and unary linear regression analysis. Moreover, the influence of mining on the ecological environment of the Gobi mining area was quantitatively evaluated by the random forest model (RF) and difference-in-difference (DID) approach. The results indicated that the value of IRSEI in HSQ had typically decreased over the last 30a. The ecological environment in most areas of the study area was poor and fair levels. The ecological environment of the whole study area showed a decreasing pattern from southeast to northwest. The proportion of degraded area (52.33 %) was much higher than that of improved area (0.39 %). The average residual before and after mining in HSQ were -0.1011 and -0.2323, respectively, which were much higher than that of the whole study area (‐0.0330 and -0.0658, respectively), indicating that the mining activities in HSQ harmed the ecological environment and aggravated the degradation of the ecological environment. The impact of mining activities on the ecological environment from 2000 to 2021 was ‐0.138 using DID. The results from the multiple regression model (MR), RF, and DID during the pre-mining period (2000−2011) were -0.0709, -0.1011, and -0.1345, respectively, while they became -0.1765, -0.2323, and -0.1963 during the post-mining period (2012−2020), respectively. The latter was worse than the former, all showing that the mining activities of HSQ had resulted in a negative effect on the ecological environment. It also demonstrated that the negative value of mining from the MR, RF, and DID have a very similar change trend and was near in value. This verified the feasibility of DID and RF in quantitative analysis of the ecological environment. The ecological environment quality of HSQ was mainly affected by climate change, and less influenced by mining, the contribution rates of both in the IRSEI improved area were 88.48 % and 11.52 %, respectively; and in the degraded area were 69.45 % and 30.55 %, respectively. Therefore, the Gobi mining area should pay attention to the protection of the ecosystem while developing coal. Planting vegetation can promote the governance and restoration of the ecological environment in the mining area.