Evaluation of different boosting ensemble machine learning models and novel deep learning and boosting framework for head-cut gully erosion susceptibility

Innovation through Artificial Intelligence in Triage Systems for Resource Optimization in Future Pandemics

Artificial intelligence (AI) systems are already being used in various healthcare areas. Similarly, they can offer many advantages in hospital emergency services. The objective of this work is to demonstrate that through the novel use of AI, a trained system can be developed to detect patients at potential risk of infection in a new pandemic more quickly than standardized triage systems. This identification would occur in the emergency department, thus allowing for the early implementation of organizational preventive measures to block the chain of transmission.

MATERIALS AND METHODS

In this study, we propose the use of a machine learning system in emergency department triage during pandemics to detect patients at the highest risk of death and infection using the COVID-19 era as an example, where rapid decision making and comprehensive support have becoming increasingly crucial. All patients who consecutively presented to the emergency department were included, and more than 89 variables were automatically analyzed using the extreme gradient boosting (XGB) algorithm.

RESULTS

The XGB system demonstrated the highest balanced accuracy at 91.61%. Additionally, it obtained results more quickly than traditional triage systems. The variables that most influenced mortality prediction were procalcitonin level, age, and oxygen saturation, followed by lactate dehydrogenase (LDH) level, C-reactive protein, the presence of interstitial infiltrates on chest X-ray, and D-dimer. Our system also identified the importance of oxygen therapy in these patients.

CONCLUSIONS

These results highlight that XGB is a useful and novel tool in triage systems for guiding the care pathway in future pandemics, thus following the example set by the well-known COVID-19 pandemic.

Physics-informed machine learning algorithms for forecasting sediment yield: an analysis of physical consistency, sensitivity, and interpretability

The sediment transport, involving the movement of the bedload and suspended sediment in the basins, is a critical environmental concern that worsens water scarcity and leads to degradation of land and its ecosystems. Machine learning (ML) algorithms have emerged as powerful tools for predicting sediment yield. However, their use by decision-makers can be attributed to concerns regarding their consistency with the involved physical processes. In light of this issue, this study aims to develop a physics-informed ML approach for predicting sediment yield. To achieve this objective, Gaussian, Center, Regular, and Direct Copulas were employed to generate virtual combinations of physical of the sub-basins and hydrological datasets. These datasets were then utilized to train deep neural network (DNN), conventional neural network (CNN), Extra Tree, and XGBoost (XGB) models. The performance of these models was compared with the modified universal soil loss equation (MUSLE), which serves as a process-based model. The results demonstrated that the ML models outperformed the MUSLE model, exhibiting improvements in Nash-Sutcliffe efficiency (NSE) of approximately 10%, 18%, 32%, and 41% for the DNN, CNN, Extra Tree, and XGB models, respectively. Furthermore, through Sobol sensitivity and Shapley additive explanation-based interpretability analyses, it was revealed that the Extra Tree model displayed greater consistency with the physical processes underlying sediment transport as modeled by MUSLE. The proposed framework provides new insights into enhancing the accuracy and applicability of ML models in forecasting sediment yield while maintaining consistency with natural processes. Consequently, it can prove valuable in simulating process-related strategies aimed at mitigating sediment transport at watershed scales, such as the implementation of best management practices.

Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches

Floods are natural occurrences that pose serious risks to human life and the environment, including significant property and infrastructure damage and subsequent socioeconomic challenges. Recent floods in Cheongju County, South Korea have been linked to river overflow. In this study, we created flood susceptibility maps of Cheongju, South Korea using machine learning techniques including support vector regression (SVR), boosted tree (BOOST), and long short-term memory (LSTM) algorithms, based on environmental factors. Potentially influential variables were selected based on flood data gathered through field surveys; these included the slope, aspect, length-slope factor, wind exposition index, terrain wetness index, plan curvature, normalized difference water index, geology, soil drainage, soil depth, soil texture, land use type, and forest density. To improve the robustness of the flood susceptibility model, the most influential factors were identified using the frequency ratio method. Implementing machine learning techniques like SVR and BOOST produced encouraging outcomes, achieving the area under the curve (AUC) of 83.16% and 86.70% for training, and 81.65% and 86.43% for testing, respectively. While, the LSTM algorithm showed superior flood susceptibility mapping performance, with an AUC value of 87.01% for training and 86.91% for testing, demonstrating its robust performance and reliability in accurately assessing flood susceptibility. The results of this study enhance our understanding of flood susceptibility in South Korea and demonstrate the potential of the proposed approach for informing and guiding crucial regional policy decisions, contributing to a more resilient and prepared future.

Systemic Lupus Erythematosus: How Machine Learning Can Help Distinguish between Infections and Flares

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune ailment that impacts multiple bodily systems and manifests with varied clinical manifestations. Early detection is considered the most effective way to save patients' lives, but detecting severe SLE activity in its early stages is proving to be a formidable challenge. Consequently, this work advocates the use of Machine Learning (ML) algorithms for the diagnosis of SLE flares in the context of infections. In the pursuit of this research, the Random Forest (RF) method has been employed due to its performance attributes. With RF, our objective is to uncover patterns within the patient data. Multiple ML techniques have been scrutinized within this investigation. The proposed system exhibited around a 7.49% enhancement in accuracy when compared to k-Nearest Neighbors (KNN) algorithm. In contrast, the Support Vector Machine (SVM), Binary Linear Discriminant Analysis (BLDA), Decision Trees (DT) and Linear Regression (LR) methods demonstrated inferior performance, with respective values around 81%, 78%, 84% and 69%. It is noteworthy that the proposed method displayed a superior area under the curve (AUC) and balanced accuracy (both around 94%) in comparison to other ML approaches. These outcomes underscore the feasibility of crafting an automated diagnostic support method for SLE patients grounded in ML systems.

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.

Assessing multi-hazard susceptibility to cryospheric hazards: Lesson learnt from an Alaskan example

Classifying a given landscape on the basis of its susceptibility to surface processes is a standard procedure in low to mid-latitudes. Conversely, these procedures have hardly been explored in periglacial regions. However, global warming is radically changing this situation and will change it even more in the future. For this reason, understanding the spatial and temporal dynamics of geomorphological processes in peri-arctic environments can be crucial to make informed decisions in such unstable environments and shed light on what changes may follow at lower latitudes. For this reason, here we explored the use of data-driven models capable of recognizing locations prone to develop retrogressive thaw slumps (RTSs) and/or active layer detachments (ALDs). These are cryospheric hazards induced by permafrost degradation, and their development can negatively affect human settlements or infrastructure, change the sediment budget and release greenhouse gases. Specifically, we test a binomial Generalized Additive Modeling structure to estimate the probability of RST and ALD occurrences in the North sector of the Alaskan territory. The results we obtain show that our binary classifiers can accurately recognize locations prone to RTS and ALD, in a number of goodness-of-fit (AUCRTS = 0.83; AUCALD = 0.86), random cross-validation (mean AUCRTS = 0.82; mean AUCALD = 0.86), and spatial cross-validation (mean AUCRTS = 0.74; mean AUCALD = 0.80) routines. Overall, our analytical protocol has been implemented to build an open-source tool scripted in Python where all the operational steps are automatized for anyone to replicate the same experiment. Our protocol allows one to access cloud-stored information, pre-process it, and download it locally to be integrated for spatial predictive purposes.

Machine learning, a new tool for the detection of immunodeficiency patterns in systemic lupus erythematosus

Systemic lupus erythematosus (SLE) is a complex autoimmune disease that affects several organs and causes variable clinical symptoms. Early diagnosis is currently the most effective way to save the lives of patients with SLE. But it is very difficult to detect in the early stages of the disease. Because of this, this study proposes a machine learning system to help diagnose patients with SLE. To carry out the research, the extreme gradient boosting method has been implemented due to its performance characteristics, as it allows high performance, scalability, accuracy, and low computational load. From this method we try to recognize patterns in the data obtained from patients, which allow the classification of SLE patients with high accuracy and differentiate these patients from controls. Several machine learning methods have been analyzed in this study. The proposed method achieves a higher prediction value of patients who may suffer from SLE than the rest of the compared systems. The proposed algorithm achieved an improvement in accuracy of 4.49% over k-Nearest Neighbors. As for the Support Vector Machine and Gaussian Naive Bayes (GNB) methods, they achieved a lower performance than the proposed one, reaching values of 83% and 81%, respectively. It should be noted that the proposed system showed a higher area under the curve (90%) and a balanced accuracy (90%) than the other machine learning methods. This study shows the usefulness of ML techniques for identifying and predicting SLE patients. These results demonstrate the possibility of developing automatic diagnostic support systems for SLE patients based on machine learning techniques.

Method for Classifying Schizophrenia Patients Based on Machine Learning

Schizophrenia is a chronic and severe mental disorder that affects individuals in various ways, particularly in their ability to perceive, process, and respond to stimuli. This condition has a significant impact on a considerable number of individuals. Consequently, the study, analysis, and characterization of this pathology are of paramount importance. Electroencephalography (EEG) is frequently utilized in the diagnostic assessment of various brain disorders due to its non-intrusiveness, excellent resolution and ease of placement. However, the manual analysis of electroencephalogram (EEG) recordings can be a complex and time-consuming task for healthcare professionals. Therefore, the automated analysis of EEG recordings can help alleviate the burden on doctors and provide valuable insights to support clinical diagnosis. Many studies are working along these lines. In this research paper, the authors propose a machine learning (ML) method based on the eXtreme Gradient Boosting (XGB) algorithm for analyzing EEG signals. The study compares the performance of the proposed XGB-based approach with four other supervised ML systems. According to the results, the proposed XGB-based method demonstrates superior performance, with an AUC value of 0.94 and an accuracy value of 0.94, surpassing the other compared methods. The implemented system exhibits high accuracy and robustness in accurately classifying schizophrenia patients based on EEG recordings. This method holds the potential to be implemented as a valuable complementary tool for clinical use in hospitals, supporting clinicians in their clinical diagnosis of schizophrenia.

Artificial Intelligence-Based Speech Analysis System for Medical Support

PURPOSE

Prior research has indicated that stroke can influence the symptoms and presentation of neurogenic bladder, with various patterns emerging, including abnormal facial and linguistic characteristics. Language patterns, in particular, can be easily recognized. In this paper, we propose a platform that accurately analyzes the voices of stroke patients with neurogenic bladder, enabling early detection and prevention of the condition.

METHODS

In this study, we developed an artificial intelligence-based speech analysis diagnostic system to assess the risk of stroke associated with neurogenic bladder disease in elderly individuals. The proposed method involves recording the voice of a stroke patient while they speak a specific sentence, analyzing it to extract unique feature data, and then offering a voice alarm service through a mobile application. The system processes and classifies abnormalities, and issues alarm events based on analyzed voice data.

RESULTS

In order to assess the performance of the software, we first obtained the validation accuracy and training accuracy from the training data. Subsequently, we applied the analysis model by inputting both abnormal and normal data and tested the outcomes. The analysis model was evaluated by processing 30 abnormal data points and 30 normal data points in real time. The results demonstrated a high test accuracy of 98.7% for normal data and 99.6% for abnormal data.

CONCLUSION

Patients with neurogenic bladder due to stroke experience long-term consequences, such as physical and cognitive impairments, even when they receive prompt medical attention and treatment. As chronic diseases become increasingly prevalent in our aging society, it is essential to investigate digital treatments for conditions like stroke that lead to significant sequelae. This artificial intelligence-based healthcare convergence medical device aims to provide patients with timely and safe medical care through mobile services, ultimately reducing national social costs.

Exploring the Dominant Features and Data-driven Detection of Polycystic Ovary Syndrome through Modified Stacking Ensemble Machine Learning Technique

Polycystic ovary syndrome (PCOS) is the most frequent endocrinological anomaly in reproductive women that causes persistent hormonal secretion disruption, leading to the formation of numerous cysts within the ovaries and serious health complications. But the real-world clinical detection technique for PCOS is very critical since the accuracy of interpretations being substantially dependent on the physician's expertise. Thus, an artificially intelligent PCOS prediction model might be a feasible additional technique to the error prone and time-consuming diagnostic technique. In this study, a modified ensemble machine learning (ML) classification approach is proposed utilizing state-of-the-art stacking technique for PCOS identification with patients' symptom data; employing five traditional ML models as base learners and then one bagging or boosting ensemble ML model as the meta-learner of the stacked model. Furthermore, three distinct types of feature selection strategies are applied to pick different sets of features with varied numbers and combinations of attributes. To evaluate and explore the dominant features necessary for predicting PCOS, the proposed technique with five variety of models and other ten types of classifiers is trained, tested and assessed utilizing different feature sets. As outcomes, the proposed stacking ensemble technique significantly enhances the accuracy in comparison to the other existing ML based techniques in case of all varieties of feature sets. However, among various models investigated to categorize PCOS and non-PCOS patients, the stacking ensemble model with 'Gradient Boosting' classifier as meta learner outperforms others with 95.7% accuracy while utilizing the top 25 features selected using Principal Component Analysis (PCA) feature selection technique.

Evaluation and classification of obfuscated Android malware through deep learning using ensemble voting mechanism

With the rise in popularity and usage of Android operating systems, malicious applications are targeted by applying innovative ways and techniques. Today, malware becomes intelligent that uses several ways of obfuscation techniques to hide its functionality and evade anti-malware engines. For mainstream smartphone users, Android malware poses a severe security danger. An obfuscation approach, however, can produce malware versions that can evade current detection strategies and dramatically lower the detection accuracy. Attempting to identify Android malware obfuscation variations, this paper proposes an approach to address the challenges and issues related to the classification and detection of malicious obfuscated variants. The employed detection and classification scheme uses both static and dynamic analysis using an ensemble voting mechanism. Moreover, this study demonstrates that a small subset of features performs consistently well when they are derived from the basic malware (non-obfuscated), however, after applying a novel feature-based obfuscation approach, the study shows a drastic change indicating the relative importance of these features in obfuscating benign and malware applications. For this purpose, we present a fast, scalable, and accurate mechanism for obfuscated Android malware detection based on the Deep learning algorithm using real and emulator-based platforms. The experiments show that the proposed model detects malware effectively and accurately along with the identification of features that are usually obfuscated by malware attackers.

Image-driven hydrological parameter coupled identification of flood plain wetland conservation and restoration sites

A good many works focus on wetland vulnerability; some works also explore restoration sites at a very limited spatial extent. But the satellite image-driven hydrological data-based approach adopted in this work is absolutely new. Moreover, existing work only focused on identifying restoration sites in the present context, but for devising long-term sustainable planning, predicted hydrological parameters based on possible restoration sites may be an effective tool. Considering this, the present work focused on exploring hydrological data (water presence frequency (WPF), hydro-period (HP) and water depth (WD)) from time-series satellite images. This exploration may resolve the hydrological data scarcity of wetland over the wider geographical areas. Using these parameters, we developed wetland restoration and conservation sites for different historical years (2008, 2018) and predicted years (2028) using ensemble machine learning (EML) models. From the analysis, it was found that water depth, hydro-period and WPF became poorer over the period, and the trend may seem to continue in predicted years. Among the applied EML models, Random Subspace (RS) predicted wetland restoration and conservation sites precisely over others. The predicted area under high-priority restoration sites is 34% in 2018, which was 14% in 2008. In 2028, 12% more areas may fall in this priority level. Wetland away from main streams (mainly ortho-fluvial wetland) and fringe wetland parts should be given more priority for restoration. These present and predicted information will effectively help to frame sustainable wetland restoration planning.

Understanding land degradation induced by gully erosion from the perspective of different geoenvironmental factors

Complex interrelationships between landscape-level geoenvironmental factors and natural phenomena have rendered land degradation control measures ineffective. For control to be effective, this study argues that the interactions between different geoenvironmental factors and gully erosion (as an indicator of land degradation) should be more fully investigated and spatially mapped. To do so, gully locations of the Konduran watershed, Iran, were detected in the field and modeled in response to seventeen geoenvironmental factors using three machine learning methods, i.e., multivariate adaptive regression splines (MARS), random forest (RF), regularized random forest (RRF), and Bayesian generalized linear model (Bayesian GLM). The models' performance was validated, the relationship of gully occurrence with each factor was quantified, the probability of gully erosion (i.e., land degradation) was retrospectively estimated, and the spatially explicit maps of land degradation susceptibility were produced. Based on the area under the receiver operating characteristic curve (AUC), the RRF and MARS models with AUC = 0.98 achieved the greatest goodness-of-fit with the training dataset, whereas the RF model with AUC = 0.83 showed the greatest ability in predicting future gully occurrences. Further scrutinization using the sensitivity and specificity metrics demonstrated the efficiency of the RF model for correctly classifying the gully (sensitivity-training = 92%; sensitivity-validation = 90%) and non-gully (specificity-training = 95%; specificity-validation = 68%) pixels. Nearly 13% of the study area ended up being the hardest hit region due to their general characteristics of distance from roads and rives, altitude, and normalized difference vegetation index (NDVI) that were identified as the most influential factors in gully erosion occurrence. Given the resolution quality and reliable predictive accuracy, our spatially explicit maps of land susceptibility to gully erosion can be used by authorities and urban planners for identifying the target areas for rehabilitation and making more informed decisions for infrastructure development. Although our study was strictly focused on a certain region, our recommendations and implications are of global significance.

Choosing the Right Horizontal Resolution for Gully Erosion Susceptibility Mapping Using Machine Learning Algorithms: A Case in Highly Complex Terrain

Gully erosion susceptibility (GES) maps are essential for managing land resources and erosion control. Choosing the optimal horizontal resolution in GES mapping is a challenge. In this study, the optimal resolution for GES mapping in a complex loess hilly area on the Chinese Loess Plateau was tested using two machine learning algorithms. Unmanned aerial vehicle (UAV) images with a 9 cm resolution and GNSS RTK field-measured data were employed as base datasets, and 11 factors were used in the machine learning models. A series of horizontal resolutions, from 0.5–30 m, was used to determine which was the optimal level and how the resolution influenced the GES mapping. The results showed that the optimal resolution for GES mapping was 2.5–5 m in the loess hilly area, for both the random forest (RF) and extreme gradient-boosting (XGBoost) machine learning algorithms employed in this study. High resolutions overestimated the probability of gully erosion in stable regions, and it became difficult to identify gully and non-gully regions at too-coarse resolutions. The variable importance for GES mapping changed with the resolution and varied among variables. Slope gradient, land use, and contributing area were, in general, the three most critical factors. Land use remained an important factor at all the tested resolution levels. The importance of the slope gradient was underestimated at coarse resolutions (10–30 m), and the importance of the contributing area was underestimated at resolutions that were comparatively fine (0.5–1 m). This study provides an essential reference for selecting the optimal resolution for gully mapping, and thus, offers support for approaches attempting to map gullies using UAV.

Predicting the dust events frequency around a degraded ecosystem and determining the contribution of their controlling factors using gradient boosting-based approaches and game theory

This study was aimed to evaluate the performance of gradient boosting machine (GBM) and extreme gradient boosting (XGB) models with linear, tree, and DART boosters to predict monthly dust events frequency (MDEF) around a degraded wetland in southwestern Iran. The monthly required data for a long-term period from 1988 to 2018 were obtained through ground stations and satellite imageries. The best predictors were selected among the eighteen climatic, terrestrial, and hydrological variables based on the multicollinearity (MC) test and the Boruta algorithm. The models' performance was evaluated using the Taylor diagram. Game theory (i.e., SHAP values: SHV) was used to determine the contribution of factors controlling MDEF in different seasons. Mean wind speed, maximum wind speed, rainfall, standardized precipitation evapotranspiration index (SPEI), soil moisture, erosive winds frequency, vapor pressure, vegetation area, water body area, and dried bed area of the wetland were confirmed as the best variables for predicting the MDEF around the studied wetland. The XGB-linear and XGB-tree showed a higher capability in predicting the MDEF variations in the summer and spring seasons. However, the XGB-Dart yielded better than XGB-linear and XGB-tree models in predicting the MDEF during the autumn and winter seasons. Rainfall (SHV = 1.6), surface water discharge (SHV = 2.4), mean wind speed (SHV = 10.1), and erosive winds frequency (SHV = 1.6) had the highest contribution in predicting the target variable in winter, spring, summer, and autumn, respectively. These findings demonstrate the effectiveness of the gradient boosting-based approaches and game theory in determining the factors affecting MDEF around a destroyed international wetland in southwestern Iran and the findings may be used to diminish their impacts on residents of this region of Iran.

Predicting soil erosion susceptibility associated with climate change scenarios in the Central Highlands of Sri Lanka

Soil erosion hazard is one of the prominent climate hazards that negatively impact countries' economies and livelihood. According to the global climate index, Sri Lanka is ranked among the first ten countries most threatened by climate change during the last three years (2018-2020). However, limited studies were conducted to simulate the impact of the soil erosion vulnerability based on climate scenarios. This study aims to assess and predict soil erosion susceptibility using climate change projected scenarios: Representative Concentration Pathways (RCP) in the Central Highlands of Sri Lanka. The potential of soil erosion susceptibility was predicted to 2040, depending on climate change scenarios, RCP 2.6 and RCP 8.5. Five models: revised universal soil loss (RUSLE), frequency ratio (FR), artificial neural networks (ANN), support vector machine (SVM) and adaptive network-based fuzzy inference system (ANFIS) were selected as widely applied for hazards assessments. Eight geo-environmental factors were selected as inputs to model the soil erosion susceptibility. Results of the five models demonstrate that soil erosion vulnerability (soil erosion rates) will increase 4%-22% compared to the current soil erosion rate (2020). The predictions indicate average soil erosion will increase to 10.50 t/ha/yr and 12.4 t/ha/yr under the RCP 2.6 and RCP 8.5 climate scenario in 2040, respectively. The ANFIS and SVM model predictions showed the highest accuracy (89%) on soil erosion susceptibility for this study area. The soil erosion susceptibility maps provide a good understanding of future soil erosion vulnerability (spatial distribution) and can be utilized to develop climate resilience.

Predicting crop root concentration factors of organic contaminants with machine learning models

Accurate prediction of uptake and accumulation of organic contaminants by crops from soils is essential to assessing human exposure via the food chain. However, traditional empirical or mechanistic models frequently show variable performance due to complex interactions among contaminants, soils, and plants. Thus, in this study different machine learning algorithms were compared and applied to predict root concentration factors (RCFs) based on a dataset comprising 57 chemicals and 11 crops, followed by comparison with a traditional linear regression model as the benchmark. The RCF patterns and predictions were investigated by unsupervised t-distributed stochastic neighbor embedding and four supervised machine learning models including Random Forest, Gradient Boosting Regression Tree, Fully Connected Neural Network, and Supporting Vector Regression based on 15 property descriptors. The Fully Connected Neural Network demonstrated superior prediction performance for RCFs (R² =0.79, mean absolute error [MAE] = 0.22) over other machine learning models (R² =0.68-0.76, MAE = 0.23-0.26). All four machine learning models performed better than the traditional linear regression model (R² =0.62, MAE = 0.29). Four key property descriptors were identified in predicting RCFs. Specifically, increasing root lipid content and decreasing soil organic matter content increased RCFs, while increasing excess molar refractivity and molecular volume of contaminants decreased RCFs. These results show that machine learning models can improve prediction accuracy by learning nonlinear relationships between RCFs and properties of contaminants, soils, and plants.

Mapping the spatial and temporal variability of flood hazard affected by climate and land-use changes in the future

The predicts current and future flood risk in the Kalvan watershed of northwestern Markazi Province, Iran. To do this, 512 flood and non-flood locations were identified and mapped. Twenty flood-risk factors were selected to model flood risk using several machine learning techniques: conditional inference random forest (CIRF), the gradient boosting model (GBM), extreme gradient boosting (XGB) and their ensembles. To investigate the future (year 2050) effects of changing climates and changing land use on future flood risk, a general circulation model (GCM) with representative concentration pathways (RCPs) of the 2.6 and 8.5 scenarios by 2050 was tested for impacts on 8 precipitation variables. In addition, future land uses in 2050 was prepared using a CA-Markov model. The performances of the flood risk models were validated with Receiver Operating Characteristic-Area Under Curve (ROC-AUC) and other statistical analyses. The AUC value of the ROC curve indicates that the ensemble model had the highest predictive power (AUC = 0.83) and was followed by GBM (AUC = 0.80), XGB (AUC = 0.79), and CIRF (AUC = 0.78). The results of climate and land use changes on future flood-prone areas showed that the areas classified as having moderate to very high flood risk will increase by 2050. Due to the changes occurring with land uses and in climates, the area classified as moderate to very high risk increased in the predictions from all four models. The areal proportion classes of the risk zones in 2050 under the RCP 2.6 scenario using the ensemble model have changed of the following proportions from the current distribution Very Low = -12.04 %, Low = -8.56 %, Moderate = +1.56 %, High = +11.55 %, and Very High = +7.49 %. The RCP 8.5 scenario has caused the following changes from the present percentages: Very Low = -14.48 %, Low = -6.35 %, Moderate = +4.54 %, High = +10.61 %, and Very High = +5.67 %. The results of current and future flood risk mapping can aid planners and flood hazard managers in their efforts to mitigate impacts.

Gully Erosion Susceptibility Assessment in the Kondoran Watershed Using Machine Learning Algorithms and the Boruta Feature Selection

Gully erosion susceptibility mapping is an essential land management tool to reduce soil erosion damages. This study investigates gully susceptibility based on multiple diagnostic analysis, support vector machine and random forest algorithms, and also a combination of these models, namely the ensemble model. Thus, a gully susceptibility map in the Kondoran watershed of Iran was generated by applying these models on the occurrence and non-occurrence points (as the target variable) and several predictors (slope, aspect, elevation, topographic wetness index, drainage density, plan curvature, distance to streams, lithology, soil texture and land use). The Boruta algorithm was used to select the most effective variables in modeling gully erosion susceptibility. The area under the receiver operating characteristic curve (AUC), the receiver operating characteristics, and true skill statistics (TSS) were used to assess the model performance. The results indicated that the ensemble model had the best performance (AUC = 0.982, TSS = 0.93) compared to the others. The most effective factors in gully erosion susceptibility mapping of the study region were topological, anthropogenic, and geological. The methodology and variables of this study can be used in other regions to control and mitigate the gully erosion phenomenon by applying biophilic and regenerative techniques at the locations of the most influential factors.