An interpretable deep learning model to map land subsidence hazard.

The main goal of this research is the interpretability of deep learning (DL) model output (e.g., CNN and LSTM) used to map land susceptibility to subsidence hazard by means of different techniques. For this purpose, an inventory map of land subsidence (LS) is prepared based on fieldwork and a record of LS presence points, and 16 features controlling LS were mapped. Thereafter, 11 effective features controlling LS were identified by means of a particle swarm optimization (PSO) algorithm, which was then used as input in the CNN and LSTM predictive models. To address the inherent black box nature of DL models, six interpretation methods (feature interaction, permutation importance plot (PFIM), bar plot, SHapley Additive exPlanations (SHAP) main plot, heatmap plot, and waterfall plot) were used to interpret the predictive model outputs. Both models (CNN and LSTM) had AUC > 90 and therefore provided excellent accuracy for mapping LS hazard. According to the most accurate model-the CNN predictive model-the range from very low to very high hazard classes occupied 20%, 20%, 25%, 16.3%, and 18.7% of the study area, respectively. According to three plots (bar plot, SHAP main plot, and heatmap plot), which were constructed based on the SHAP value, distance from the well, GDR and DEM were identified as the three most important features with the highest impact on the DL model output. The results of the waterfall plot indicate two effective features consisting of distance from the well and coarse fragment, and two effective features comprising landuse and DEM, contributed negatively and positively to LS, respectively. Overall, these explanation techniques can address critical concerns with respect to the interpretability of sophisticated DL predictive models.

Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion.

Gully erosion possess a serious hazard to critical resources such as soil, water, and vegetation cover within watersheds. Therefore, spatial maps of gully erosion hazards can be instrumental in mitigating its negative consequences. Among the various methods used to explore and map gully erosion, advanced learning techniques, especially deep learning (DL) models, are highly capable of spatial mapping and can provide accurate predictions for generating spatial maps of gully erosion at different scales (e.g., local, regional, continental, and global). In this paper, we applied two DL models, namely a simple recurrent neural network (RNN) and a gated recurrent unit (GRU), to map land susceptibility to gully erosion in the Shamil-Minab plain, Hormozgan province, southern Iran. To address the inherent black box nature of DL models, we applied three novel interpretability methods consisting of SHaply Additive explanation (SHAP), ceteris paribus and partial dependence (CP-PD) profiles and permutation feature importance (PFI). Using the Boruta algorithm, we identified seven important features that control gully erosion: soil bulk density, clay content, elevation, land use type, vegetation cover, sand content, and silt content. These features, along with an inventory map of gully erosion (based on a 70 % training dataset and 30 % test dataset), were used to generate spatial maps of gully erosion using DL models. According to the Kolmogorov-Smirnov (KS) statistic performance assessment measure, the simple RNN model (with KS = 91.6) outperformed the GRU model (with KS = 66.6). Based on the results from the simple RNN model, 7.4 %, 14.5 %, 18.9 %, 31.2 % and 28 % of total area of the plain were classified as very-low, low, moderate, high and very-high hazard classes, respectively. According to SHAP plots, CP-PD profiles, and PFI measures, soil silt content, vegetation cover (NDVI) and land use type had the highest impact on the model's output. Overall, the DL modelling techniques and interpretation methods used in this study proved to be helpful in generating spatial maps of soil erosion hazard, especially gully erosion. Their interpretability can support watershed sustainable management.

Novel integrated modelling based on multiplicative long short-term memory (mLSTM) deep learning model and ensemble multi-criteria decision making (MCDM) models for mapping flood risk.

Flood risk assessment is a key step in flood management and mitigation, and flood risk maps provide a quantitative measure of flood risk. Therefore, integration of deep learning - an updated version of machine learning techniques - and multi-criteria decision making (MCDM) models can generate high-resolution flood risk maps. In this study, a novel integrated approach has been developed based on multiplicative long short-term memory (mLSTM) deep learning models and an MCDM ensemble model to map flood risk in the Minab-Shamil plain, southern Iran. A flood hazard map generated by the mLSTM model is based on nine critical features selected by GrootCV (distance to the river, vegetation cover, variables extracted from DEM (digital elevation model) and river density) and a flood inventory map (70% and 30% data were randomly selected as training and test datasets, respectively). The values of all criteria used to assess model accuracy performance (except Cohens kappa for train dataset = 86, and for test dataset = 84) achieved values greater than 90, which indicates that the mLSTM model performed very well for the generation of a spatial flood hazard map. According to the spatial flood hazard map produced by mLSTM, the very low, low, moderate, high and very high classes cover 26%, 35.3%, 20.5%, 11.2% and 7% of the total area, respectively. Flood vulnerability maps were produced by the combinative distance-based assessment (CODAS), the evaluation based on distance from average solution (EDAS), and the multi-objective optimization on the basis of simple ratio analysis (MOOSRA), and then validated by Spearman's rank correlation coefficients (SRC). Based on the SRC, the three models CODAS, EDAS, and MOOSRA showed high-ranking correlations with each other, and all three models were then used in the ensemble process. According to the CODAS-EDAS-MOOSRA ensemble model, 21.5%, 34.2%, 23.7%, 13%, and 7.6% of the total area were classified as having a very low to very high flood vulnerability, respectively. Finally, a flood risk map was generated by the combination of flood hazard and vulnerability maps produced by the mLSTM and MCDM ensemble model. According to the flood risk map, 27.4%, 34.3%, 14.8%, 15.7%, and 7.8% of the total area were classified as having a very low, low, moderate, high, and very high flood risk, respectively. Overall, the integration of mLSTM and the MCDM ensemble is a promising tool for generating precise flood risk maps and provides a useful reference for flood risk management.

Stacking- and voting-based ensemble deep learning models (SEDL and VEDL) and active learning (AL) for mapping land subsidence.

This contribution presents a novel methodology based on the feature selection, ensemble deep learning (EDL) models, and active learning (AL) approach for prediction of land subsidence (LS) hazard and rate, and its uncertainty in an area involving two important plains - the Minab and Shamil-Nian plains - in the Hormozgan province, southern Iran. The important features controlling LS hazard were identified by ridge regression. Then, two EDL models were constructed by stacking (SEDL) and voting (VEDL) five dense deep learning (DL) models (model 1 to model 5) for mapping LS hazard. Thereafter, the predictive model performance was assessed by a precision-recall curve and Kolmogorov-Smirnov (KS) plot. A partial dependence plot (PDP), individual conditional expectation plots (ICEP), game theory, and a sensitivity analysis were used for the interpretability of the predictive DL model. According to SEDL - a model with higher accuracy - 34% (1624 km2), 14.7% (698 km2), and 19.2% (912 km2) of the total area were classified as being of very low, low, and moderate hazards, whereas 17.7% (845 km2) and 14.4% (683 km2) of area were classified as being of high and very high hazards, respectively. Based on all interpretability techniques, aquifer loss or groundwater drawdown is the most important feature controlling LS hazard, and it having the greatest impact on the SEDL model output. Based on a Taylor diagram and R2 as model performance assessment indicators, SEDL-AL (with R2 > 95% for training and test datasets) performed better than SEDL for quantify LS rate, the rate of LS ranging between 0 and 48.1 cm. The highest rate of LS occurred in the Minab plain - an area located downstream of the Minab Esteghlal dam. SEDL-AL was used to quantify the uncertainty associated with the LS rate. The observed values fell within predictions provided by SEDL-AL, which indicates a high accuracy of our predictive model. Overall, our newly developed modeling techniques are helpful tools for the spatial mapping of LS susceptibility and rate, and its uncertainty.

Assessment of the uncertainty and interpretability of deep learning models for mapping soil salinity using DeepQuantreg and game theory.

This research introduces a new combined modelling approach for mapping soil salinity in the Minab plain in southern Iran. This study assessed the uncertainty (with 95% confidence limits) and interpretability of two deep learning (DL) models (deep boltzmann machine-DBM) and a one dimensional convolutional neural networks (1DCNN)-long short-term memory (LSTM) hybrid model (1DCNN-LSTM) for mapping soil salinity by applying DeepQuantreg and game theory (Shapely Additive exPlanations (SHAP) and permutation feature importance measure (PFIM)), respectively. Based on stepwise forward regression (SFR)-a technique for controlling factor selection, 18 of 47 potential controls were selected as effective factors. Inventory maps of soil salinity were generated based on 476 surface soil samples collected for measuring electrical conductivity (ECe). Based on Taylor diagrams, both DL models performed well (RMSE < 20%), but the 1DCNN-LSTM hybrid model performed slightly better than the DBM model. The uncertainty range associated with the ECe values predicted by both models estimated using DeepQuantilreg were similar (0-25 dS/m for the 1DCNN-LSTM hybrid model and 2-27 dS/m for DBM model). Based on the SFR and PFIM (permutation feature importance measure)-a measure in game theory, four controls (evaporation, sand content, precipitation and vertical distance to channel) were selected as the most important factors for soil salinity in the study area. The results of SHAP (Shapely Additive exPlanations)-the second measure used in game theory-suggested that five factors (evaporation, vertical distance to channel, sand content, cation exchange capacity (CEC) and digital elevation model (DEM)) have the strongest impact on model outputs. Overall, the methodology used in this study is recommend for applications in other regions for mapping environmental problems.

Spatial modelling of soil salinity: deep or shallow learning models?

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.

RAIRS2 a new expert system for diagnosing tuberculosis with real-world tournament selection mechanism inside artificial immune recognition system.

Tuberculosis is a major global health problem that has been ranked as the second leading cause of death from an infectious disease worldwide, after the human immunodeficiency virus. Diagnosis based on cultured specimens is the reference standard; however, results take weeks to obtain. Slow and insensitive diagnostic methods hampered the global control of tuberculosis, and scientists are looking for early detection strategies, which remain the foundation of tuberculosis control. Consequently, there is a need to develop an expert system that helps medical professionals to accurately diagnose the disease. The objective of this study is to diagnose tuberculosis using a machine learning method. Artificial immune recognition system (AIRS) has been used successfully for diagnosing various diseases. However, little effort has been undertaken to improve its classification accuracy. In order to increase the classification accuracy, this study introduces a new hybrid system that incorporates real tournament selection mechanism into the AIRS. This mechanism is used to control the population size of the model and to overcome the existing selection pressure. Patient epacris reports obtained from the Pasteur laboratory in northern Iran were used as the benchmark data set. The sample consisted of 175 records, from which 114 (65 %) were positive for TB, and the remaining 61 (35 %) were negative. The classification performance was measured through tenfold cross-validation, root-mean-square error, sensitivity, and specificity. With an accuracy of 100 %, RMSE of 0, sensitivity of 100 %, and specificity of 100 %, the proposed method was able to successfully classify tuberculosis cases. In addition, the proposed method is comparable with top classifiers used in this research.