Ambient carbon monoxide (CO) and particulate matters (PMs) are two important air pollutants in urban areas with known impacts on fetuses. Hence, this study measured some biochemistry factors of 200 neonates with birth dates from January 19 to October 12, 2020, including the birth weight and height and the serum levels of ALT, AST, ALP, GGT, and TSH. The Support Vector Machine-fitted land-use regression approach was used to predict the spatio-temporal variability of intra-urban PM 2.5 and CO concentrations by month during the pregnancy period of the cases employing 5 variables of Digital Elevation Model (DEM), slope, and distance from Compressed Natural Gas (CNG) stations, Bus Rapid Transit (BRT) stations, and mines and industries. Spearman correlation analysis (p < 0.05) was performed between the neonate indices and mean monthly PM 2.5 and CO concentrations at the exact residential address of maternal cases and their nearby areas in 250, 500, 1000, 1500, and 2000 m-radius buffer rings. All modeling efforts succeeded in predicting CO and PM 2.5 levels with acceptable adjusted r² values. Northern Isfahan had relatively higher CO and PM 2.5 concentrations due to its adjacency to low-vegetated open lands and its high traffic load as compared to southern areas. The correlation results between the neonate biochemistry indices and mean PM 2.5 and CO concentrations were mostly positive in most buffer rings, especially in the >500 m-radius buffer rings for PM 2.5 and in the 2000 m-radius rings for CO. Although the correlation results of PM 2.5 followed a detectable trend in the buffer rings, the associations between CO and the neonate biochemistry indices differed significantly between the buffer rings. Results showed that increasing mean monthly concentration of CO and PM 2.5 may stimulate further production of liver enzymes while decreasing the birth weight and height.

Identifying factors that influence the land surface temperature (LST) of urban forests can help improve simulations and predictions of spatial patterns of urban cool islands. This requires a quantitative analytical method that combines spatial statistical analysis with multi-source observational data. The purpose of this study was to reveal how human activities and ecological factors jointly influence LST in clustering regions (hot or cool spots) of urban forests. Using Xiamen City, China from 1996 to 2006 as a case study, we explored the interactions between human activities and ecological factors, as well as their influences on urban forest LST. Population density was selected as a proxy for human activity. We integrated multi-source data (forest inventory, digital elevation models (DEM), population, and remote sensing imagery) to develop a database on a unified urban scale. The driving mechanism of urban forest LST was revealed through a combination of multi-source spatial data and spatial statistical analysis of clustering regions. The results showed that the main factors contributing to urban forest LST were dominant tree species and elevation. The interactions between human activity and specific ecological factors linearly or nonlinearly increased LST in urban forests. Strong interactions between elevation and dominant species were generally observed and were prevalent in either hot or cold spots areas in different years. In conclusion, quantitative studies based on spatial statistics and GeogDetector models should be conducted in urban areas to reveal interactions between human activities, ecological factors, and LST.

The spatiotemporal variation and driving force of the Normalized Difference Vegetation Index (NDVI) are helpful to ecological environment protection and natural resource management. Using the Sen and Mann–Kendall methods, Hurt index, and the Geodetector, this study investigated the temporal and spatial changes and driving forces of NDVI during 1982–2015. The results showed that (1) From 1982 to 2015, the high vegetation coverage was mainly distributed in the Qinling Mountains and the Daba Mountains, while the low vegetation coverage was in high altitude areas in the west, low altitude in the east, and the Hanjiang River valley. (2) NDVI in the Qinba Mountains increased continuously accounting for 81.1%, with 68% showing slow growth. In the future, only 37.8% of the vegetation will have significant change. The area of vegetation increase will be greater than the area of decrease. (3) NDVI increased firstly and then decreased with the increase of altitude, reaching the maximum value at 1100 m. NDVI showed a trend of fluctuating growth. It reached the maximum value of 0.86 in 2015. (4) Through the Geodetector, the main factors affecting NDVI were natural factors mainly including rainfall, soil type, and digital elevation model (DEM), while human activities, including population density, had little influence on NDVI. Natural environment factors and human activities together had a greater impact on the spatial distribution of NDVI. This study could provide help for the sustainable development of the natural environment in the Qinba Mountains.

The information about different morphometric parameters of any watershed is necessary for better watershed management and planning. This study aimed to investigate morphometric characteristics, to assess the soil erosion risk, and to prioritize different sub-watersheds of the Koyna River basin, India, with two different approaches using geospatial technology. Different linear, shape, and relief parameters of the basin were estimated and analyzed. The linear and shape parameters indicated that the basin has less flood hazard. The relief parameters indicated that the basin has moderate roughness and unevenness. The parallel drainage pattern is dominant inside the basin due to the highly elongated nature of the basin. The bifurcation ratio (Rb) indicated lithological and geological variations inside the basin. Two different approaches namely morphometric analysis and empirical Revised Universal Soil Loss Equation (RUSLE) method were applied for prioritization of different sub-watersheds. Rainfall, soil, digital elevation model (DEM), and normalized difference vegetation index (NDVI) data were used for identifying erosion-prone zones with RUSLE analysis. Based on RUSLE analysis, the entire study area was divided into five soil erosion risk classes namely very slight (80.43 %), slight (14.94 %), moderate (3.21 %), severe (0.79 %), and very severe (0.63%), respectively. Most of the study area was found to be under a very slight soil erosion vulnerability class based on the RUSLE approach. The conservation practices should be carried out as per the priority ranking of different sub-watershed based on soil erosion rates. The results found in this study can surely assist in the implementation of soil conservation planning and management practices to reduce soil loss in the Koyna River basin of India.

Twenty daily time step–based SWAT simulation models for the Duhok, Adhaim and Dokan dam watersheds, in Iraq, were implemented using five land cover (LC) and digital elevation model (DEM) of different resolutions. The optimal LC and DEM for computing the most accurate streamflow for each watershed were specified. Results indicated that delineation of the flat watersheds is significantly affected by the DEM resolution and there was no evident trend on the computation of watersheds’ total areas, boundaries, number of subbasins and stream networks. Moreover, there is no significant trend between the increase in LC and DEM resolutions and accuracy of the computed streamflow. The most accurate streamflows for the Duhok, Adhaim and Dokan watersheds were computed using LC (DEM) of 30 m, 1000 m and 1000 m.

In addition to global population growth due to migration from rural areas to urban areas, population density is constantly increasing in certain regions, thereby necessitating the introduction of new settlements in these regions. However, in the selection of settlement areas, no sufficient preliminary examinations have been conducted; consequently, various natural disasters may cause significant life and property losses. Herein, the most suitable settlement areas were determined using GIS (geographic information systems) in Canik District, where the population is continuously increasing. Therefore, this study aimed to incorporate a new perspective into studies on this subject. Within the scope of the study, landslide and flood risks, which are among the most important natural disasters in the region, were primarily evaluated, and high-risk areas were determined. Elevation, slope, aspect, curvature, lithology, topographic humidity index (TWI), and proximity to river parameters were used to produce flood susceptibility maps. A digital elevation model (DEM) of the study area was produced using contours on the 1/25,000 scaled topographic map. The elevation, slope, aspect, curvature, and TWI parameters were produced from the DEM using the relevant analysis routines of ArcGIS software. The raster map of each parameter was divided into 5 subclasses using the natural breaks classification method. In the reclassified raster maps, the most flood-sensitive or flood-prone subclasses were assigned a value of 5, and the least sensitive subclasses were assigned a value of 1. Then, the reclassified maps of the 7 parameters were collected using the “map algebra” function of ArcGIS 10.5 software, and the flood susceptibility index (FSI) map of the study area was obtained. The flood susceptibility map of the study area was obtained by dividing the FSI into 5 subclasses (very low, low, moderate, high, and very high) according to the natural breaks classification method. Thereafter, suitable and unsuitable areas in terms of biocomfort, which affects people’s health, peace, comfort, and psychology and is significant in terms of energy efficiency, were determined. At the last stage of the study, the most suitable settlement areas that were suitable in terms of both biocomfort and low levels of landslide and flood risks were determined. The calculated proportion of such areas to the total study area was only 2.1%. Therefore, because these areas were insufficient for the establishment of new settlements, areas that had low landslide and flood risks but were unsuitable for biocomfort were secondarily determined; the ratio of these areas was calculated as 56.8%. The remaining areas were inconvenient for the establishment of settlements due to the risk of landslides and floods; the ratio of these areas was calculated as 41.1%. This study is exemplary in that the priority for the selection of settlement areas was specified, and this method can be applied for selecting new settlements for each region considering different criteria. Due to the risk of landslides or flooding in the study area, the areas unsuitable for establishing a settlement covered approximately 41.1% of the total study area. The areas that had low flood and landslide risks but were suitable for biocomfort constituted only 2.1% of the study area. In approximately 56.8% of the study area, the risk of landslides or floods was low, and these areas were unsuitable in terms of biocomfort. Therefore, these areas were secondarily preferred as settlement areas. The most suitable areas for settlements constituted only 0.19% of the total study area, and these areas will not be able to meet the increasing demand for settlement area. Therefore, it is recommended to select areas that do not have the risk of landslides and floods but are unsuitable for biocomfort. This study reveals that grading should be performed in the selection of settlement areas. When choosing a settlement area in any region, possible natural disasters in the region should be identified first, and these disasters should be ordered in terms of their threat potential. Moreover, biocomfort areas suitable for settlements should be considered. In the next stages of settlement area selection, the criteria that affect the peace and comfort of people, such as distance to pollution sources, distance to noise sources, and proximity to natural areas, should also be evaluated. Thus, a priority order should be created for the selection of settlement areas using various other criteria.

Understanding the spatial distribution of soil salinity is required to conserve land against degradation and desertification. Against this background, this study is the first attempt to predict soil salinity in the Jaghin basin, in southern Iran, by applying and comparing the performance of four deep learning (DL) models (deep convolutional neural networks—DCNNs, dense connected deep neural networks—DenseDNNs, recurrent neural networks-long short-term memory—RNN-LSTM and recurrent neural networks-gated recurrent unit—RNN-GRU) and six shallow machine learning (ML) models (bagged classification and regression tree—BCART, cforest, cubist, quantile regression with LASSO penalty—QR-LASSO, ridge regression—RR and support vectore machine—SVM). To do this, 49 environmental landsat8-derived variables including digital elevation model (DEM)-extracted covariates, soil-salinity indices, and other variables (e.g., soil order, lithology, land use) were mapped spatially. For assessing the relationships between soil salinity (EC) and factors controlling EC, we collected 319 surficial (0–5 cm depth) soil samples for measuring soil salinity on the basis of electrical conductivity (EC). We then selected the most important features (covariates) controlling soil salinity by applying a MARS model. The performance of the DL and shallow ML models for generating soil salinity spatial maps (SSSMs) was assessed using a Taylor diagram and the Nash Sutcliff coefficient (NSE). Among all 10 predictive models, DL models with NSE ≥ 0.9 (DCNNs was the most accurate model with NSE = 0.96) were selected as the four best models, and performed better than the six shallow ML models with NSE ≤ 0.83 (QR-LASSO was the weakest predictive model with NSE = 0.50). Based on DCNNs-, the values of the EC ranged between 0.67 and 14.73 dS/m, whereas for QR-LASSO the corresponding EC values were 0.37 to 19.6 dS/m. Overall, DL models performed better than shallow ML models for production of the SSSMs and therefore we recommend applying DL models for prediction purposes in environmental sciences.

The Büyük Menderes watershed is the largest drainage watershed in Western Anatolia with an area of approximately 26,000 km². In the study area, almost 863 landslides occurred, extending over 222 km² with a mean landslide area of 0.21 km². In this study, landslide susceptibility assessments were carried out using artificial neural network method, which is one of the data-driven methods. In this study, that will contribute to the mitigation or control of the landslides caused by the reasons controlling the spatial and temporal distribution of landslides created in the GIS and MATLAB environment by using scientific and technological approaches within the framework. Since derivative activation function is also used in back-propagation artificial neural networks, its derivative is easily calculated in order not to slow down the calculation. Levenberg–Marquardt back-propagation (LM), resilient back propagation back-propagation (trainrp), scaled conjugate gradient back-propagation (trainscg), conjugate gradient with Powell/Beale restarts back-propagation (traincgb), and Fletcher-Powell conjugate gradient back-propagation (traincgf) algorithms are used, which constantly interrogate the link between the input parameter and the result output, and at least one cell’s output is given as an input to any other cell. Geology, digital elevation model, slope, topographic wetness index, roughness index, plan, profile curvatures, and proximity to active faults and rivers were used as landslide conditioning factors. In susceptibility assessments, landslides were separated by 70% analysis, 15% test, and 15% validation datasets by random selection method. The performances of the landslide susceptibility maps were assessed by the area under the ROC curve (AUC), accuracy (ACC), precision, recall, F1 score, Kappa test error histogram, and confusion matrix, respectively. The area under the receiver operating characteristic curves, analysis, testing, validation, landslides, and study areas were found between 0.873 and 0.911. The susceptibility map had a high prediction rate in which high and very high susceptible zones corresponded to 26% of the study area including 82% of the recorded landslides.

Ice masses and snow of Hunza River Basin (HRB) are an important primary source of fresh water and lifeline for downstream inhabitants. Changing climatic conditions seriously put an impact on these available ice and snow masses. These glaciers may affect downstream population by glacial lake outburst floods (GLOF) and surge events due to climatic variation. So, monitoring of these glaciers and available ice masses is important. This research delivers an approach for dynamics of major glaciers of the Hunza River Basin. We delineated 27 major glaciers of HRB and examined their status by using Landsat (OLI, ETM+, ETM, TM), digital elevation model (DEM) over the period of 1990–2018. In 1990, the total area covered by these glaciers is about 2589.75 ± 86 km² and about 2565.12 ± 68km² in 2018. Our results revealed that from 2009 to 2015, glacier coverage of HRB advanced with a mean annual advance rate of 2.22 ± 0.1 km² a⁻¹. Conversely, from 1994 to 1999, the strongest reduction in glacier area with a mean rate of − 3.126 ± 0.3 km² a⁻¹ is recorded. The glaciers of HRB are relatively stable compared to Hindukush, Himalayan, and Tibetan Plateau region of the world. The steep slope glacier’s retreat rate is more than that of gentle slope glaciers, and the glaciers below an elevation of 5000 m above sea level change significantly. Based on climate data from 1995 to 2018, HRB shows a decreasing trend in temperature and increasing precipitation. The glacier area’s overall retreat is due to an increase in summer temperature while the glacier advancement is induced possibly by winter and autumn precipitation.

A three-dimensional interpolation method based on a digital elevation model (DEM) was developed to assess the impact of mining and metallurgical activity on the Claro River (Hidalgo, Mexico). This method was used to analyze the spatial concentration of manganese in sediments, water, and fish (viscera and muscle). Input data correspond to chemical manganese (Mn) analysis of the aforementioned environmental matrices, mining discharge volumes, and rainfall data. The three-dimensional model made it possible to (a) define Mn dispersion (19 km for sediments and 13 km for viscera); (b) identify northern meanders of the Claro River as areas of Mn accumulation in sediments and fish; and (c) determine river features that influence Mn concentration in fish. Results indicate that Mn concentration increases in areas receiving industrial discharges, as well as in meanders located near Acuimantla village. Total Mn levels in the water are between < 0.01 and 6.57 mg/L, while soluble and colloidal Mn concentrations range from < 0.01 to 0.49 mg/L. The highest Mn values in the water (total Mn: 6.57 mg/L and soluble-colloidal Mn: 0.49 mg/L) were detected in tributary rivers near industrial discharge sites. The concentration in water compared with that in sediments (160–213,867 mg/kg) and fish (viscera: 5–5236 mg/kg and muscle: 10.7–398.8 mg/kg) indicates low solubility of this mineral. The geoaccumulation index (Igeo) and contamination factor (CF) show that sediment composition has been affected.