Interpreting optimised data-driven solution with explainable artificial intelligence (XAI) for water quality assessment for better decision-making in pollution management.

In Saudi Arabia, water pollution and drinking water scarcity pose a major challenge and jeopardise the achievement of sustainable development goals. The urgent need for rapid and accurate monitoring and assessment of water quality requires sophisticated, data-driven solutions for better decision-making in water management. This study aims to develop optimised data-driven models for comprehensive water quality assessment to enable informed decisions that are critical for sustainable water resources management. We used an entropy-weighted arithmetic technique to calculate the Water Quality Index (WQI), which integrates the World Health Organization (WHO) standards for various water quality parameters. Our methodology incorporated advanced machine learning (ML) models, including decision trees, random forests (RF) and correlation analyses to select features essential for identifying critical water quality parameters. We developed and optimised data-driven models such as gradient boosting machines (GBM), deep neural networks (DNN) and RF within the H2O API framework to ensure efficient data processing and handling. Interpretation of these models was achieved through a three-pronged explainable artificial intelligence (XAI) approach: model diagnosis with residual analysis, model parts with permutation-based feature importance and model profiling with partial dependence plots (PDP), accumulated local effects (ALE) plots and individual conditional expectation (ICE) plots. The quantitative results revealed insightful findings: fluoride and residual chlorine had the highest and lowest entropy weights, respectively, indicating their differential effects on water quality. Over 35% of the water samples were categorised as 'unsuitable' for consumption, highlighting the urgency of taking action to improve water quality. Amongst the optimised models, the Random Forest (model 79) and the Deep Neural Network (model 81) proved to be the most effective and showed robust predictive abilities with R2 values of 0.96 and 0.97 respectively for testing dataset. Model profiling as XAI highlighted the significant influence of key parameters such as nitrate, total hardness and pH on WQI predictions. These findings enable targeted water quality improvement measures that are in line with sustainable water management goals. Therefore, our study demonstrates the potential of advanced, data-driven methods to revolutionise water quality assessment in Saudi Arabia. By providing a more nuanced understanding of water quality dynamics and enabling effective decision-making, these models contribute significantly to the sustainable management of valuable water resources.

Evaluating the impact of urbanization on the urban heat islands through integrated radius and non-linear regression approach.

Urban heat islands (UHIs) are a significant environmental problem, exacerbating the urban climate and affecting human health in the Asir region of Saudi Arabia. The need to understand the spatio-temporal dynamics of UHI in the context of urban expansion is crucial for sustainable urban planning. The aim of this study was to quantify the changes in land use and land cover (LULC) and urbanization, assess the expansion process of UHI, and analyze its connectivity in order to develop strategies to mitigate UHI in an urban context over a 30-year period from 1990 to 2020. Using remote sensing data, LULC changes were analyzed with a random forest model. LULC change rate (LCCR), land cover intensity (LCI), and landscape expansion index (LEI) were calculated to quantify urbanization. The land surface temperature for the study period was calculated using the mono-window algorithm. The UHI effect was analyzed using an integrated radius and non-linear regression approach, fitting SUHI data to polynomial curves and identifying turning points based on the regression derivative for UHI intensity belts to quantify the expansion and intensification of UHI. Landscape metrics such as the aggregation index (AI), landscape shape index (LSI), and four other matrices were calculated to assess UHI morphology and connectivity of the UHI. In addition, the LEI was adopted to measure the extent of UHI growth patterns. From 1990 to 2020, the study area experienced significant urbanization, with the built-up area increasing from 69.40 to 338.74 km2, an increase of 1.923 to 9.385% of the total area. This expansion included growth in peripheral areas of 129.33 km2, peripheral expansion of 85.40 km2, and infilling of 3.80 km2. At the same time, the UHI effect intensified with an increase in mean LST from 40.55 to 46.73 °C. The spatial extent of the UHI increased, as shown by the increase in areas with an LST above 50 °C from 36.58 km2 in 1990 to 133.52 km2 in 2020. The connectivity of the UHI also increased, as shown by the increase in the AI from 38.91 to 41.30 and the LSI from 56.72 to 93.64, reflecting a more irregular and fragmented urban landscape. In parallel to these urban changes, the area classified as UHI increased significantly, with the peripheral areas expanding from 23.99 km2 in the period 1990-2000 to 80.86 km2 in the period 2000-2020. Peripheral areas also grew significantly from 36.42 to 96.27 km2, contributing to an overall more pronounced and interconnected UHI effect by 2020. This study provides a comprehensive analysis of urban expansion and its thermal impacts. It highlights the need for integrated urban planning that includes strategies to mitigate the UHI effect, such as improving green infrastructure, optimizing land use, and improving urban design to counteract the negative effects of urbanization.

Spatiotemporal assessment of the nexus between urban sprawl and land surface temperature as microclimatic effect: implications for urban planning.

Rapid urbanisation has led to significant environmental and climatic changes worldwide, especially in urban heat islands where increased land surface temperature (LST) poses a major challenge to sustainable urban living. In the city of Abha in southwestern Saudi Arabia, a region experiencing rapid urban growth, the impact of such expansion on LST and the resulting microclimatic changes are still poorly understood. This study aims to explore the dynamics of urban sprawl and its direct impact on LST to provide important insights for urban planning and climate change mitigation strategies. Using the random forest (RF) algorithm optimised for land use and land cover (LULC) mapping, LULC models were derived that had an overall accuracy of 87.70%, 86.27% and 93.53% for 1990, 2000 and 2020, respectively. The mono-window algorithm facilitated the derivation of LST, while Markovian transition matrices and spatial linear regression models assessed LULC dynamics and LST trends. Notably, built-up areas grew from 69.40 km2 in 1990 to 338.74 km2 in 2020, while LST in urban areas showed a pronounced warming trend, with temperatures increasing from an average of 43.71 °C in 1990 to 50.46 °C in 2020. Six landscape fragmentation indices were then calculated for urban areas over three decades. The results show that the Largest Patch Index (LPI) increases from 22.78 in 1990 to 65.24 in 2020, and the number of patches (NP) escalates from 2,531 in 1990 to an impressive 10,710 in 2020. Further regression analyses highlighted the morphological changes in the cities and attributed almost 97% of the LST variability to these urban patch dynamics. In addition, water bodies showed a cooling trend with a temperature decrease from 33.76 °C in 2000 to 29.69 °C in 2020, suggesting an anthropogenic influence. The conclusion emphasises the urgent need for sustainable urban planning to counteract the warming trends associated with urban sprawl and promote climate resilience.

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models.

Landslide susceptibility mapping is essential for reducing the risk of landslides and ensuring the safety of people and infrastructure in landslide-prone areas. However, little research has been done on the development of well-optimized Elman neural networks (ENN), deep neural networks (DNN), and artificial neural networks (ANN) for robust landslide susceptibility mapping (LSM). Additionally, there is a research gap regarding the use of Bayesian optimization and the derivation of SHapley Additive exPlanations (SHAP) values from optimized models. Therefore, this study aims to optimize DNN, ENN, and ANN models using Bayesian optimization for landslide susceptibility mapping and derive SHAP values from these optimized models. The LSM models have been validated using the receiver operating characteristics curve, confusion matrix, and other twelve error matrices. The study used six machine learning-based feature selection techniques to identify the most important variables for predicting landslide susceptibility. The decision tree, random forest, and bagging feature selection models showed that slope, elevation, DFR, annual rainfall, LD, DD, RD, and LULC are influential variables, while geology and soil texture have less influence. The DNN model outperformed the other two models, covering 7839.54 km2 under the very low landslide susceptibility zone and 3613.44 km2 under the very high landslide susceptibility zone. The DNN model is better suited for generating landslide susceptibility maps, as it can classify areas with higher accuracy. The model identified several key factors that contribute to the initiation of landslides, including high elevation, built-up and agricultural land use, less vegetation, aspect (north and northwest), soil depth less than 140 cm, high rainfall, high lineament density, and a low distance from roads. The study's findings can help stakeholders make informed decisions to reduce the risk of landslides and ensure the safety of people and infrastructure in landslide-prone areas.

Evaluating the influence of road construction on landslide susceptibility in Saudi Arabia's mountainous terrain: a Bayesian-optimised deep learning approach with attention mechanism and sensitivity analysis.

In the mountainous region of Asir region of Saudi Arabia, road construction activities are closely associated with frequent landslides, posing significant risks to both human life and infrastructural development. This highlights an urgent need for a highly accurate landslide susceptibility map to guide future development and risk mitigation strategies. Therefore, this study aims to (1) develop robust well-optimised deep learning (DL) models for predicting landslide susceptibility and (2) conduct a comprehensive sensitivity analysis to quantify the impact of each parameter influencing landslides. To achieve these aims, three advanced DL models-Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Bayesian-optimised CNN with an attention mechanism-were rigorously trained and validated. Model validation included eight matrices, calibration curves, and Receiver Operating Characteristic (ROC) and Precision-Recall curves. Multicollinearity was examined using Variance Inflation Factor (VIF) to ensure variable independence. Additionally, sensitivity analysis was used to interpret the models and explore the influence of parameters on landslide. Results showed that road networks significantly influenced the areas identified as high-risk zones. Specifically, in the 1-km buffer around roadways, CNN_AM identified 10.42% of the area as 'Very High' susceptibility-more than double the 4.04% indicated by DNN. In the extended 2-km buffer zone around roadways, Bayesian CNN_AM continued to flag a larger area as Very High risk (7.46%), in contrast to DNN's 3.07%. In performance metrics, CNN_AM outshined DNN and regular CNN models, achieving near-perfect scores in Area Under the Curve (AUC), precision-recall, and overall accuracy. Sensitivity analysis highlighted 'Soil Texture', 'Geology', 'Distance to Road', and 'Slope' as crucial for landslide prediction. This research offers a robust, high-accuracy model that emphasises the role of road networks in landslide susceptibility, thereby providing valuable insights for planners and policymakers to proactively mitigate landslide risks in vulnerable zones near existing and future road infrastructure.

Analysis of urban streets and surface thermal characteristics using thermal imaging camera in residential streets of Gurugram City, India.

The thermal properties of the urban landscape are significantly affected by various human activities such as changing land use patterns, the construction of buildings and other impervious surfaces, and the development of transport systems. Urbanization often leads to the replacement of natural landscapes with impervious surfaces such as concrete and asphalt, which have a higher heat absorption capacity and lower emissivity. The continuous displacement of urban landscapes by impermeable surfaces therefore leads to an increase in urban temperatures, ultimately causing the development of the urban heat island (UHI) phenomenon. The study aims to analyze the thermal properties of physical elements in residential streets of Gurugram City using a thermal imaging camera to investigate the relationship between ambient air temperature and thermal behavior of surface materials. The study shows that the compact streets are 2-4 °C cooler than the open streets due to mutual shading of the buildings. Similarly, the temperature in the light-colored buildings is 1.5-4 °C lower than the dark buildings in the streets. In addition, a simple coat of paint over a plastered wall is much cooler than granite stone wall cladding. The study also showed how shading, whether by mutual shading or vegetative shading, can lower the surface temperature of urban materials. Building codes and design guidelines can therefore use such studies to make urban exteriors more pleasant by recommending lighter colors, plants, and local materials.

Assessing landscape fragmentation due to urbanization in English Bazar Municipality, Malda, India, using landscape metrics.

Urbanization in India is having a significant impact on the environment and human health, as built-up areas are expanding while vegetation and water bodies are declining. To mitigate the negative effects of urbanization, there is an urgent need to monitor and manage the growth of cities through the creation of smart cities. Accurately identifying and mapping urban expansion patterns is crucial to achieving this goal, but this is currently lacking in India. To address this gap, this study takes a comprehensive approach to examining the processes of urban expansion in English Bazar Municipality, Malda, India. The study employs the random forest (RF) method for land use and land cover (LULC) mapping for the years 2001, 2011, and 2021 and then uses the frequency approach, landscape homogeneity, and fragmentation to model urban expansion over the same time period. The study also employs several landscape matrices to quantify urban expansion. The results of the study reveal a substantial increase in built-up areas from 601.26 hectares in 2001 to 859.13 hectares in 2021, accompanied by a corresponding decline in vegetation, cropland, and open land. This land use transition process has also led to increased fragmentation of the landscape. The spatiotemporal landscape homogeneity analysis identifies two transition zones (zone 2 and zone 1) surrounding the stable zone, which capture the new, small, isolated built-up areas and show a progression of urban expansion from 2001 to 2021. Overall, the study provides valuable insights into the changes in urban expansion and fragmentation in English Bazar Municipality. To promote sustainable urban development and enhance the quality of life for residents, it is important for stakeholders and the government to prioritize the conservation and creation of green and blue spaces. This can be accomplished through the incorporation of green infrastructure, smart city principles, community engagement and education, and partnerships with local businesses.

Carbon capture and biocatalytic oxygen production of photosystem II from thylakoids and microalgae on nanobiomaterials.

Enhanced carbon capture and oxygen production via water splitting was observed by controlling the plasmon-induced resonance energy transfer (PIRET) for photosystem II (PSII) in thylakoid extracts and spirulina assembled on gold nanoparticle (AuNP) dimer arrays. The two types of vertical (V) and horizontal (H) AuNP dimer arrays were uniformly inserted inside pore diameter-controlled templates. Based on the theoretical calculations, the longitudinal mode of the H AuNP dimer array was found to be sensitive to the nanogap distances between the two AuNPs in resonance with the absorption at P680 of the PSII. The longitudinal modes that interacted with P680 of PSII increased from the V to the H conformer. The optical properties from the H AuNP dimer array caused overlapping absorbance and photoluminescence with PSII, and the H AuNP dimer arrays exhibited a significant increase in carbon capture and oxygen generation rates in comparison with those of the bare PSII protein complex under light irradiation via the controlled PIRET process.

Alfa glucosidase inhibitory, anti inflammatory activities and a new furanocoumarin derivative of Ruellia tuberosa.

Rullia tuberosa L. is used for treatment of diabetes mellitus, anti-inflammation, etc. However, its hypoglycaemic and anti inflammatory activities has not been investigated so far. In the present study, the α-glucosidase inhibitory, anti inflammatory activities of the extract of this plant were investigated. Our results showed that the crude extract as well as ethyl acetate and methanol fractions showed α-glucosidase inhibitory activity with IC50 of 15.84, 4.73 and 8.27 µg/ml, respectively. In addition, the hexane and ethyl acetate fractions are capable of inhibiting LPS-induced NO production with IC50 of 17.41 and 23.95 µg/mL, respectively. From the ethyl acetate and methanol fractions, eight compounds, including isobargaptol 5-O-ß-D-glucopyranoside (1), syringaresinol (2), catechin (3), pulmatin (4), stigmast-4-en-3-on (4), verbascoside (5), hydroxymethylfurfural (6), rutin (7), and homoplantaginin (8) were extracted and isolated. Their chemical structures were elucidated by spectroscopic method including MS, 1 D and 2 D- NMR and comparison with the literature values.

Risk factors of Streptococcus suis infection in Vietnam. A case-control study.

BACKGROUND: Streptococcus suis infection, an emerging zoonosis, is an increasing public health problem across South East Asia and the most common cause of acute bacterial meningitis in adults in Vietnam. Little is known of the risk factors underlying the disease. METHODS AND FINDINGS: A case-control study with appropriate hospital and matched community controls for each patient was conducted between May 2006 and June 2009. Potential risk factors were assessed using a standardized questionnaire and investigation of throat and rectal S. suis carriage in cases, controls and their pigs, using real-time PCR and culture of swab samples. We recruited 101 cases of S. suis meningitis, 303 hospital controls and 300 community controls. By multivariate analysis, risk factors identified for S. suis infection as compared to either control group included eating "high risk" dishes, including such dishes as undercooked pig blood and pig intestine (OR(1) = 2.22; 95%CI = [1.15-4.28] and OR(2) = 4.44; 95%CI = [2.15-9.15]), occupations related to pigs (OR(1) = 3.84; 95%CI = [1.32-11.11] and OR(2) = 5.52; 95%CI = [1.49-20.39]), and exposures to pigs or pork in the presence of skin injuries (OR(1) = 7.48; 95%CI = [1.97-28.44] and OR(2) = 15.96; 95%CI = [2.97-85.72]). S. suis specific DNA was detected in rectal and throat swabs of 6 patients and was cultured from 2 rectal samples, but was not detected in such samples of 1522 healthy individuals or patients without S. suis infection. CONCLUSIONS: This case control study, the largest prospective epidemiological assessment of this disease, has identified the most important risk factors associated with S. suis bacterial meningitis to be eating 'high risk' dishes popular in parts of Asia, occupational exposure to pigs and pig products, and preparation of pork in the presence of skin lesions. These risk factors can be addressed in public health campaigns aimed at preventing S. suis infection.

Diagnosis of pulmonary tuberculosis in HIV-positive patients by microscopic observation drug susceptibility assay.

The microscopic observation drug susceptibility assay (MODS) is a novel and promising test for the early diagnosis of tuberculosis (TB). We evaluated the MODS assay for the early diagnosis of TB in HIV-positive patients presenting to Pham Ngoc Thach Hospital for Tuberculosis and Lung Diseases in southern Vietnam. A total of 738 consecutive sputum samples collected from 307 HIV-positive individuals suspected of TB were tested by smear, MODS, and the mycobacteria growth indicator tube method (MGIT). The diagnostic sensitivity and specificity of MODS compared to the microbiological gold standard (either smear or MGIT) were 87 and 93%, respectively. The sensitivities of smear, MODS, and MGIT were 57, 71, and 75%, respectively, against clinical gold standard (MODS versus smear, P<0.001; MODS versus MGIT, P=0.03). The clinical gold standard was defined as patients who had a clinical examination and treatment consistent with TB, with or without microbiological confirmation. For the diagnosis of smear-negative patients, the sensitivities of MODS and MGIT were 38 and 45%, respectively (P=0.08). The median times to detection using MODS and MGIT were 8 and 11 days, respectively, and they were 11 and 17 days, respectively, for smear-negative samples. The original bacterial/fungal contamination rate of MODS was 1.1%, while it was 2.6% for MGIT. The cross-contamination rate of MODS was 4.7%. In conclusion, MODS is a sensitive, specific, and rapid test that is appropriate for the detection of HIV-associated TB; its cost and ease of use make it particularly useful in resource-limited settings.

Immunological and biochemical correlates of adjunctive dexamethasone in Vietnamese adults with bacterial meningitis.

Adjunctive treatment to improve outcome from bacterial meningitis has centered on dexamethasone. Among Vietnamese patients with bacterial meningitis, cerebrospinal fluid (CSF) opening pressure and CSF:plasma glucose ratios were significantly improved and levels of CSF cytokines interleukin (IL)-6, IL-8, and IL-10 and were all statistically significantly lower after treatment in patients who were randomized to dexamethasone, compared with levels in patients who received placebo.