The accelerated warming in the Arctic poses serious risks to freshwater ecosystems by altering streamflow and river thermal regimes. However, limited research on Arctic River water temperatures exists due to data scarcity and the absence of robust methodologies, which often focus on large, major river basins. To address this, we leveraged the newly released, extensive AKTEMP data set and advanced machine learning techniques to develop a Long Short-Term Memory (LSTM) model. By incorporating ERA5-Land reanalysis data and integrating physical understanding into data-driven processes, our model advanced river water temperature predictions in ungauged, snow- and permafrost-affected basins in Alaska. Our model outperformed existing approaches in high-latitude regions, achieving a median Nash-Sutcliffe Efficiency of 0.95 and root mean squared error of 1.0 degrees C. The LSTM model learned air temperature, soil temperature, solar radiation, and thermal radiation-factors associated with energy balance-were the most important drivers of river temperature dynamics. Soil moisture and snow water equivalent were highlighted as critical factors representing key processes such as thawing, melting, and groundwater contributions. Glaciers and permafrost were also identified as important covariates, particularly in seasonal river water temperature predictions. Our LSTM model successfully captured the complex relationships between hydrometeorological factors and river water temperatures across varying timescales and hydrological conditions. This scalable and transferable approach can be potentially applied across the Arctic, offering valuable insights for future conservation and management efforts.

In this study, a novel data-driven approach is carried out to predict the pore pressure generation of liquefiable clean sands during cyclic loading. An extensive and comprehensive database of actual stress-controlled cyclic simple shear test results in terms of pore pressure time histories is gathered from a large number of experiments. While the classical machine learning (ML) algorithms help predict the number of liquefaction cycles in a few models, the desired level of accuracy in predicting the actual trend and robustness in pore pressure build-up is only achieved in deep learning (DL) methods. Results indicate that the Long-Short Term Memory (LSTM) working model, employed with Stacked LSTM and the Windowing data processing method, is necessary for making fairly good cyclic pore pressure build-up predictions. This study proposes a model that can ultimately be utilised to predict the pore pressure response of in-situ liquefiable sandy soil layers without resorting to plasticity-based complex theoretical models, which has been the current practice. The robustness achieved in the model reassures the reliability of the study, raising confidence in developing data-driven constitutive models for soils that have the potential to replace conventional plasticity-based theories.

Most of the robust artificial intelligence (AI)-based constitutive models are developed with synthetic datasets generated from traditional constitutive models. Therefore, they fundamentally rely on the traditional constitutive models rather than laboratory test results. Also, their potential use within geotechnical engineering communities is limited due to the unavailability of datasets along with the model code files. In this study, the data-driven constitutive models are developed using only laboratory test databases and deep learning (DL) techniques. The laboratory database was prepared by conducting cyclic direct simple shear (CDSS) tests on reconstituted sand, that is, PDX sand. The stacked long short-term memory (LSTM) network and its variants are considered for developing the predictive models of the shear strain (gamma [%]) and excess pore pressure ratio (ru) time histories. The suitable input parameters (IPs) are selected based on the physics behind the generation of ru and gamma (%) of the liquefiable sands. The predicted responses of gamma (%) and ru agree well in most cases and are used to predict the dynamic soil properties of the PDX sand. The same modeling framework is extended for other sand and compared with existing AI-based constitutive models to verify its practical applicability. In summary, it is observed that though the trained models predicted the time histories of ru and gamma reasonably well; however, they struggled to predict the hysteresis loops at higher cycles. Therefore, more research is needed to verify and enhance the predictability of existing AI-based models in the future before using them in practice for simulating cyclic response.

Unsaturated soil has complicated mechanical properties, such as stress path and suction history dependencies, due to the influence of the depositional environment and its own structure. To describe the complex behavior of unsaturated soils, a path-dependence aware LSTM-based framework is proposed, where the initial stress state of the soil sample is used as the initial network parameters. Compared with the LSTM model, this framework demonstrates faster training convergence and better prediction accuracy. This framework was used to simulate the mechanical behavior of unsaturated soils under complex loading paths where both stress and suction change simultaneously and is not limited to suction-controlled triaxial shear tests. The predictions using both synthetic data from the Barcelona basic model (BBM) and experimental data from Pearl clay and Nanyang expansive soil and unsaturated sand-bentonite mixtures show that the LSTM-based framework can predict phenomena such as wetting collapse, stress path dependence, strain softening, and strain hardening in unsaturated soils.

Agriculture is one of the prime economical sources of India and most of the people directly or indirectly depend on farming. The researchers are focusing on plant ailment detection and managing the imbalanced nutrition in plants. Automation is introduced in agricultural fields and most of these automation strategies use the Internet of Things (IoT) for enhance productivity and automate processes. With the help of several deep and machine learning approaches the endless decision-making performance is performed. Here, the endless decision performance shows appropriate outcomes which helps to solve the unstructured problems in smart farming. It is monitored that the traditional analysis doesn't have enough decision-making ability in the selection of fertilizer quantity that is to be used in farming. This inability leads to crop ailments and that affects the lifestyle of humans too. So, the prior detection of ailments in crops is essential. Enforcing Smart Agriculture is a hot topic in research nowadays to overcome crop damage in the future. Therefore, a new IoT-based smart farming model using deep learning is proposed to increase crop yield. By detecting disease, pests, smart irrigation, and yield, the smart farming model can reduce the amount of water and chemicals used in agriculture. This smart farming model consists of four phases a) disease prediction, b) pest detection c) smart irrigation, and d) yield prediction. In the first phase, the crop images are gathered from online datasets. The diseases in crops are predicted using Multiscale Adaptive CNN with LSTM layer (MA-CNN-LSTM), where the parameters in MA-CNN-LSTM are optimized using Advanced Mountaineering Team-Based Optimization Algorithm (AMTBO). In the second phase, the input images are given to MA-CNN-LSTM to detect crop pests. Here, the AMTBO is utilized for tuning parameters. In the third phase, the soil quality and environment data are fed into the Multi-scale Adaptive 1DCNN with LSTM layer (MA-1D CNN-LSTM) to predict the smart irrigation, where the parameter optimization is done using the AMTBO. Smart irrigation enhances the growth of crops and minimizes water usage. In the final phase, the input data such as crop quality, soil quality, and environment data are given to the MA-1D CNN-LSTM to check the overall yield prediction in an agricultural region. Here, the parameters in MA-1D CNN-LSTM are optimized via the AMTBO. The simulation results are compared with other algorithms and classification techniques to check the performance of the developed model.

Ground response analysis under earthquakes is a critical part of earthquake engineering. Experimental or numerical techniques are commonly applied to implement seismic soil response analysis. However, due to the expensive and time-consuming implementation and also uncertainties in experimental tests and numerical analyses, in this study, deep learning methods are proposed as a good alternative for nonlinear seismic soil response analysis. Long short-term memory network (LSTM) and bidirectional long short-term memory network (BiLSTM) are selected as potential candidates. Input features for the deep LSTM and Bi-LSTM structures are input ground motions at the base of the soil model. And, output features are responses in terms of time series at different locations along the depth of the soil medium. It is noted that all the responses are simultaneously predicted. A limited number of real earthquakes with various characteristics are chosen for training, validation, and testing datasets in the deep learning methods. The datasets are formed by using numerical results. The nonlinear behavior of the soil in numerical models is simulated by employing a sophisticated constitutive model of simple anisotropic SAND (SANISAND). The effectiveness of numerical results is demonstrated with the assistance of the centrifuge test. The results confirm the good performance of the proposed deep learning models for nonlinear seismic ground response prediction. The capacity of the deep learning models is inspected in both the time domain in terms of time series and the frequency domain.

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.

In order to study the impact of surface roughness on the cyclic shear characteristics of the Soil-Rock Mixture and concrete interface, a series of cyclic shear tests were conducted using a large indoor direct shear apparatus. The effects of three concrete surface roughness coefficients JRC (0.4, 9.5, 16.7), five rock content levels (0%, 25%, 50%, 75%, 100%), and three cyclic shear displacement amplitudes (1, 3, 6 mm) on interface cyclic shear stress and Soil-Rock Mixture shear deformation were analyzed. A Bidirectional Long Short-Term Memory (BoBiLSTM) model was proposed, utilizing Bayesian optimization and k-fold cross-validation for hyperparameter tuning to streamline the model parameter selection process and enhance the prediction accuracy of the stress-strain relationship under cyclic loading. The experimental results show that, under five rock content levels, as the concrete surface roughness coefficient and cyclic shear displacement amplitude increase, the interface average peak shear stress increases accordingly. The interface average peak shear stress of the sample with 75% rock content is the highest; in terms of vertical displacement, the sample with 50% rock content has the maximum displacement, while the sample with 25% rock content has the minimum. The two types of samples show different soil deformation patterns in the two shear directions during the cyclic shearing process; as the shear displacement amplitude increases from 1 mm to 3 mm and 6 mm, the greater the concrete surface roughness, the smaller the change in shear stiffness and damping ratio. Compared to traditional Long Short-Term Memory (LSTM) models, the BoBiLSTM model demonstrated improvements in the average metrics of R2, RMSE, and MAPE by 0.32%, 57.25%, and 72.32%, respectively.

Hydromechanical behaviour of unsaturated expansive soils is complex, and current constitutive models failed to accurately reproduce it. Different from conventional modelling, this study proposes a novel physics-informed neural networks (PINN)-based model utilising long short-term memory as the baseline algorithm and incorporating a physical constraint (water retention) to modify the loss function. Firstly, a series of laboratory tests on Zaoyang expansive clay, including wetting and drying cycle tests and triaxial tests, was compiled into a dataset and subsequently fed into the PINN-based model. Subsequently, a specific equation representing the soil water retention curve (SWRC) for expansive clay was derived by accounting for the influence of the void ratio, which was integrated into the PINN-based model as a physical law. The ultimate predictions from the PINN-based model are compared with experimental data of unsaturated expansive clay with excellent agreement. This study demonstrates the capability of the proposed PINN in modelling the hydromechanical response of unsaturated soils and provides an innovative approach to establish constitutive models in the unsaturated soil mechanics field.

In subtropical typhoon-prone regions, landslides are triggered by short-duration intense rainfall and prolonged periods of elevated pore-water pressure. However, fast-moving landslides pose a significant challenge for timely warning because of insufficient data on rainfall triggers and the identification of potential failure sites. Thus, our study introduces an integrated approach that combines a double-index intensity-duration (I-D) threshold, accounting for daily rainfall (R0) and 5-d effective rainfall (R5), with the MC-TRIGRS, a probabilistic physically based model, to analyze fast-moving landslide hazards at a regional scale. This approach is characterized by its innovative features: (i) it employs a double-index model to categorize rainfall events, differentiating between long-term continuous rainfall and short-term intense precipitation; (ii) it utilizes a comprehensive dataset from extensive field investigations to implement the grey wolf optimizer (GWO) -enhanced long short-term memory neural network (LSTM) to predict soil thickness distributions across the study area; and (iii) it adopts the classical Monte Carlo method to calculate failure probabilities under various rainfall scenarios, incorporating randomness in key soil parameters, such as cohesion and internal friction angle. By leveraging geotechnical data from both field and laboratory tests and integrating the accumulated knowledge, these models can be applied to the coastal mountainous basins of Eastern China, a region highly prone to landslides. Our goal was to augment the effectiveness of landslide early warning systems. Particularly, the synergistic use of rainfall empirical statistics and probabilistic physically based slope stability models is poised to bolster real-time control and risk mitigation strategies, providing a robust solution for short-term preparedness.