Static and dynamic source identification of trace elements in river and soil environments under anthropogenic activities in the Haraz plain, Northern Iran.

Unsustainable human activities have disrupted the natural cycle of trace elements, causing the accumulation of chemical pollutants and making it challenging to determine their sources due to interwoven natural and human-induced processes. A novel approach was introduced for identifying the sources and for quantifying the contribution of trace elements discharge from rivers to soils. We integrated fingerprinting techniques, soil and sediment geochemical data, geographically weighted regression model (GWR) and soil quality indices. The FingerPro package and the state-of-the-art tracer selection techniques including the conservative index (CI) and consensus ranking (CR) were used to quantify the relative contribution of different upland sub-watersheds in trace element discharge soil. Our analysis revealed that off-site sources (upland watersheds) and in-site sources (land use) both play an important role in transferring trace elements to the Haraz plain (northern Iran). The unmixing model's results suggest that the Haraz sub-watersheds exhibit a higher contribution to trace elements transfer in the Haraz plain, and therefore, require greater attention in terms of implementing soil and water conservation strategies. However, it is noteworthy that the Babolroud (adjacent to Haraz) exhibited a better performance of the model. A spatial correlation between certain heavy metals, such as As and Cu, and rice cultivation existed. Additionally, we found a significant spatial correlation between Pb and residential areas, particularly in the Amol region. Our result highlights the importance of using advanced spatial statistical techniques, such as GWR, to identify subtle but critical associations between environmental variables and sources of pollution. The methodology used comprehensively identifies dynamic trace element sourcing at the watershed scale, allowing for pollutant source identification and practical strategies for soil and water quality control. Tracer selection techniques (CI and CR) based on conservatives and consensus improve unmixing model accuracy and flexibility for precise fingerprinting.

Evaluation of multi-hazard map produced using MaxEnt machine learning technique.

Natural hazards are diverse and uneven in time and space, therefore, understanding its complexity is key to save human lives and conserve natural ecosystems. Reducing the outputs obtained after each modelling analysis is key to present the results for stakeholders, land managers and policymakers. So, the main goal of this survey was to present a method to synthesize three natural hazards in one multi-hazard map and its evaluation for hazard management and land use planning. To test this methodology, we took as study area the Gorganrood Watershed, located in the Golestan Province (Iran). First, an inventory map of three different types of hazards including flood, landslides, and gullies was prepared using field surveys and different official reports. To generate the susceptibility maps, a total of 17 geo-environmental factors were selected as predictors using the MaxEnt (Maximum Entropy) machine learning technique. The accuracy of the predictive models was evaluated by drawing receiver operating characteristic-ROC curves and calculating the area under the ROC curve-AUCROC. The MaxEnt model not only implemented superbly in the degree of fitting, but also obtained significant results in predictive performance. Variables importance of the three studied types of hazards showed that river density, distance from streams, and elevation were the most important factors for flood, respectively. Lithological units, elevation, and annual mean rainfall were relevant for detecting landslides. On the other hand, annual mean rainfall, elevation, and lithological units were used for gully erosion mapping in this study area. Finally, by combining the flood, landslides, and gully erosion susceptibility maps, an integrated multi-hazard map was created. The results demonstrated that 60% of the area is subjected to hazards, reaching a proportion of landslides up to 21.2% in the whole territory. We conclude that using this type of multi-hazard map may be a useful tool for local administrators to identify areas susceptible to hazards at large scales as we demonstrated in this research.

Novel GIS Based Machine Learning Algorithms for Shallow Landslide Susceptibility Mapping.

The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas.