Mapping of dust source susceptibility by remote sensing and machine learning techniques (case study: Iran-Iraq border)

An assessment of global land susceptibility to wind erosion based on deep-active learning modelling and interpretation techniques

Spatial accurate mapping of land susceptibility to wind erosion is necessary to mitigate its destructive consequences. In this research, for the first time, we developed a novel methodology based on deep learning (DL) and active learning (AL) models, their combination (e.g., recurrent neural network (RNN), RNN-AL, gated recurrent units (GRU), and GRU-AL) and three interpretation techniques (e.g., synergy matrix, SHapley Additive exPlanations (SHAP) decision plot, and accumulated local effects (ALE) plot) to map global land susceptibility to wind erosion. In this respect, 13 variables were explored as controlling factors to wind erosion, and eight of them (e.g., wind speed, topsoil carbon content, topsoil clay content, elevation, topsoil gravel fragment, precipitation, topsoil sand content and soil moisture) were selected as important factors via the Harris Hawk Optimization (HHO) feature selection algorithm. The four models were applied to map land susceptibility to wind erosion, and their performance was assessed by three measures consisting of area under of receiver operating characteristic (AUROC) curve, cumulative gain and Kolmogorov Smirnov (KS) statistic plots. The results revealed that GRU-AL model was considered as the most accurate, revealing that 38.5%, 12.6%, 10.3%, 12.5% and 26.1% of the global lands are grouped at very low, low, moderate, high and very high susceptibility classes to wind erosion hazard, respectively. Interpretation techniques were applied to interpret the contribution and impact of the eight input variables on the model's output. Synergy plot revealed that the soil carbon content exhibited high synergy with DEM and soil moisture on the model's predictions. ALE plot showed that soil carbon content and precipitation had negative feedback on the prediction of land susceptibility to wind erosion. Based on SHAP decision plot, soil moisture and DEM presented the highest contribution on the model's output. Results highlighted new regions at high latitudes (southern Greenland coast, hotspots in Alaska and Siberia), which exhibited high and very high land susceptibility to wind erosion.

Long-term remote sensing-based methods for monitoring air pollution and cloud cover in the Balkan countries

The use of remote sensing and GIS methodology has accelerated the processing of data on pollution, but has also raised a question about the accuracy of the same. The research focuses on four main air pollutants (CO, NO, SO2, O3), the data on which were obtained from satellite images of Landsat 8 and Landsat 9, for the period 2000-2020. The data on relative cloudiness were obtained from the database CHELSA (Climatologies at high resolution for the earth's land surface areas) for the period 1980-2010. All the data were further processed and analyzed through the procedures of numerical GIS analysis, multi-criteria analysis, supervised and unsupervised satellite classification, and pixel analysis. The results of the analysis of cloud cover in the Balkan region showed that the month with the highest cloud cover in this period was February, with the maximum of (93.18%), whereas the lowest cloud cover was in July (0.19%). The analyzed period (2000-2010) was in the middle range for the pollutants NO and SO2 and in the lower range for CO; O3. In the period 2010-2020, there were high concentrations of NO, SO2, and CO and low concentrations of O3. The most polluted cities in the last twenty years are Ordu (Turkey), Sarajevo (Bosnia and Herzegovina), and Bor (Serbia). Finally, two most extreme air pollutants in the territory of Balkan countries were SO2 and NO (2000-2020).

Intrinsic and extrinsic techniques for quantification uncertainty of an interpretable GRU deep learning model used to predict atmospheric total suspended particulates (TSP) in Zabol, Iran during the dusty period of 120-days wind

Total suspended particulates (TSP), as a key pollutant, is a serious threat for air quality, climate, ecosystems and human health. Therefore, measurements, prediction and forecasting of TSP concentrations are necessary to mitigate their negative effects. This study applies the gated recurrent unit (GRU) deep learning model to predict TSP concentrations in Zabol, Iran, during the dust period of the 120-day wind (3 June - 4 October 2014). Three uncertainty quantification (UQ) techniques consisting of the blackbox metamodel, heteroscedastic regression and infinitesimal jackknife were applied to quantify the uncertainty associated with GRU model. Permutation feature importance measure (PFIM), based on the game theory, was employed for the interpretability of the predictive model's outputs. A total of 80 TSP samples were collected and were randomly divided as training (70%) and validation (30%) datasets, while eight variables were used in the TSP prediction model. Our findings showed that GRU performed very well for TSP prediction (with r and Nash Sutcliffe coefficient (NSC) values above 0.99 for both datasets, and RMSE of 57 μg m-3 and 73 μg m-3 for training and validation datasets, respectively). Among the three UQ techniques, the infinitesimal jackknife was the most accurate one, while all the observed and predicted TSP values fell within the continence limitation estimated by the model. PFIM plots showed that wind speed and air humidity were the most and least important variables, respectively, impacting the predictive model's outputs. This is the first attempt of using an interpretable DL model for TSP prediction modelling, recommending that future research should involve aspects of uncertainty and interpretability of the predictive models. Overall, UQ and interpretability techniques have a key role in reducing the impact of uncertainties during optimization and decision making, resulting in better understanding of sophisticated mechanisms related to the predictive model.