As industrial operations move to the state, residents find that their drinking water has been promised to companies. In 2019, Corpus Christi, Texas's eighth-largest city, moved forward with plans to build a desalination plant. The facility, which was expected to be completed by 2023, at a cost of a hundred and forty million dollars, would convert seawater into fresh water to be used by the area's many refineries and chemical plants. The former mayor called it "a pretty significant day in the life of our city." In anticipation of the plant's opening, the city committed to provide tens of millions of gallons of water per day to new industrial operations, including a plastics plant co-owned by ExxonMobil and the Saudi Basic Industries Corporation, a lithium refinery for Tesla batteries, and a "specialty chemicals" plant operated by Chemours.

Google's newest AI model is going to scour the Earth and, ideally, help it out. The mission is to find out once and for all, in fine detail, what we are doing to our planet. Crucially, once the model has supposedly done this it will also, apparently, explain where we might be able to best put things in place to help our world. AlphaEarth Foundations, an offshoot of Google's DeepMind AI model, aims to leverage machine learning and all the gobs and gobs of data that Google has absorbed about our planet over the last two decades, in order to understand how specific areas are changing over time. The model uses a system called "embeddings" that takes terabytes of data collected from satellites every day, analyzes it, and compresses it down to save storage space.

Groundwater is eventually undermined by human exercises, such as fast industrialization, urbanization, over-extraction, and contamination from agrarian and urban sources. From among the different contaminants, the presence of heavy metals like cadmium (Cd), chromium (Cr), arsenic (As), and lead (Pb) proves to have serious dangers when present in huge concentrations in groundwater. Long-term usage of these poisonous components may lead to neurological disorders, kidney failure and different sorts of cancer. To address these issues, this study developed a machine learning-based predictive model to evaluate the Groundwater Quality Index (GWQI) and identify the main contaminants which are affecting the water quality. It has been achieved with the help of a hybrid machine learning model i.e. LCBoost Fusion . The model has undergone several processes like data preprocessing, hyperparameter tuning using Differential Evolution (DE) optimization, and evaluation through cross-validation. The LCBoost Fusion model outperforms individual models (CatBoost and LightGBM), by achieving low RMSE (0.6829), MSE (0.5102), MAE (0.3147) and a high R$^2$ score of 0.9809. Feature importance analysis highlights Potassium (K), Fluoride (F) and Total Hardness (TH) as the most influential indicators of groundwater contamination. This research successfully demonstrates the application of machine learning in assessing groundwater quality risks in Odisha. The proposed LCBoost Fusion model offers a reliable and efficient approach for real-time groundwater monitoring and risk mitigation. These findings will help the environmental organizations and the policy makers to map out targeted places for sustainable groundwater management. Future work will focus on using remote sensing data and developing an interactive decision-making system for groundwater quality assessment.

Ontology learning in complex domains, such as life sciences, poses significant challenges for current Large Language Models (LLMs). Existing LLMs struggle to generate ontologies with multiple hierarchical levels, rich interconnections, and comprehensive class coverage due to constraints on the number of tokens they can generate and inadequate domain adaptation. To address these issues, we extend the NeOn-GPT pipeline for ontology learning using LLMs with advanced prompt engineering techniques and ontology reuse to enhance the generated ontologies' domain-specific reasoning and structural depth. Our work evaluates the capabilities of LLMs in ontology learning in the context of highly specialized and complex domains such as life science domains. To assess the logical consistency, completeness, and scalability of the generated ontologies, we use the AquaDiva ontology developed and used in the collaborative research center AquaDiva as a case study. Our evaluation shows the viability of LLMs for ontology learning in specialized domains, providing solutions to longstanding limitations in model performance and scalability.

You may have heard about the Supreme Court's recent ruling in Sackett v. EPA that the Clean Water Act does not permit the Environmental Protection Agency to regulate the use of wetlands that are not connected at the surface to lakes, rivers and streams. While there's been plenty of analysis of the significant legal flaws in the ruling--which will greatly restrict the ability of the EPA to protect not only wetlands but our entire fresh water system--less has been said about the science undergirding the case. The reality is this: The ruling takes no consideration whatsoever of the science of water. The court ruled that protection under the CWA only applies when wetlands have "a continuous surface connection to bodies that are'waters of the United States' in their own right, so that there is no clear demarcation between'waters' and wetlands." Justice Samuel Alito arrived at this distinction by parsing the wording of the Clean Water Act as passed by Congress in 1972 and amended in 2018--specifically the words "waters of the United States"--and the opinion makes much of this means of arriving at the decision.

California's Central Valley is the national agricultural center, producing 1/4 of the nation's food. However, land in the Central Valley is sinking at a rapid rate (as much as 20 cm per year) due to continued groundwater pumping. Land subsidence has a significant impact on infrastructure resilience and groundwater sustainability. In this study, we aim to identify specific regions with different temporal dynamics of land displacement and find relationships with underlying geological composition. Then, we aim to remotely estimate geologic composition using interferometric synthetic aperture radar (InSAR)-based land deformation temporal changes using machine learning techniques. We identified regions with different temporal characteristics of land displacement in that some areas (e.g., Helm) with coarser grain geologic compositions exhibited potentially reversible land deformation (elastic land compaction). We found a significant correlation between InSAR-based land deformation and geologic composition using random forest and deep neural network regression models. We also achieved significant accuracy with 1/4 sparse sampling to reduce any spatial correlations among data, suggesting that the model has the potential to be generalized to other regions for indirect estimation of geologic composition. Our results indicate that geologic composition can be estimated using InSAR-based land deformation data. In-situ measurements of geologic composition can be expensive and time consuming and may be impractical in some areas. The generalizability of the model sheds light on high spatial resolution geologic composition estimation utilizing existing measurements.

Using algorithms and artificial intelligence, a research team led by Universidad Complutense de Madrid (UCM) has designed a tool which, in its initial trials, proved capable of predicting those areas with best access to potable groundwater in Africa, with a success rate of close to 90%. In specific terms, the papers published in Hydrology and Earth System Science and Geocarto International describe the hydrogeological mapping performed by the MLMapper software in the regions of Bamako and Koulikoro (Mali) and the region of Ouaddaï (Chad), respectively. "Ensure access to water and sanitation for all" is Sustainable Development Goal 6. In sub-Saharan Africa, groundwater plays a fundamental role in the supply of drinking water, but the percentage of wells that strike water is very often lower than 30%. "This is mainly because of a lack of hydrogeological knowledge, with the practical consequence that millions of euros of humanitarian aid are lost in fruitless drilling operations", underlines Víctor Gómez-Escalonilla Canales, a researcher at UCM's Department of Geodynamics, Stratigraphy and Palaeontology.

A group of researchers from IIT Kharagpur in West Bengal has successfully predicted the presence of arsenic in groundwater and its adverse effect on human health in affected areas using Artificial Intelligence (AI) algorithms on environmental, geological and human usage parameters. They also successfully managed to delineate the high and low arsenic zones across the Ganges River delta using AI and quantify the number of people exposed. Madhumita Chakraborty, the lead author of the paper, said, "Our AI models predict the occurrence of high arsenic in groundwater across more than half of the Ganges River delta, covering more than 25% area in each of the 19 out of 25 administrative zones in West Bengal. A total of 30.3 million people are estimated to be exposed to severely high As-hazard within the Ganges River delta." The AI findings will be a boon in the Eastern states where arsenic has been a concern, especially along the banks of the Ganga for almost two decades, putting millions of people at severe health risk.

Circulating groundwater triggered a four-year-long swarm of tiny earthquakes that rumbled beneath the Southern California town of Cahuilla, researchers report in the June 19 Science. By training computers to recognize such faint rumbles, the scientists were able not only to identify the probable culprit behind the quakes, but also to track how such mysterious swarms can spread through complex fault networks in space and time. Seismic signals are constantly being recorded in tectonically active Southern California, says seismologist Zachary Ross of Caltech. Using that rich database, Ross and colleagues have been training computers to distinguish the telltale ground movements of minute earthquakes from other things that gently shake the ground, such as construction reverberations or distant rumbles of the ocean (SN: 4/18/19). The millions of tiny quakes revealed by this machine learning technique, he says, can be used to create high-resolution, 3-D images of what lies beneath the ground's surface in a particular region.

Naturally occurring arsenic in groundwater affects millions of people worldwide. We created a global prediction map of groundwater arsenic exceeding 10 micrograms per liter using a random forest machine-learning model based on 11 geospatial environmental parameters and more than 50,000 aggregated data points of measured groundwater arsenic concentration. Our global prediction map includes known arsenic-affected areas and previously undocumented areas of concern. By combining the global arsenic prediction model with household groundwater-usage statistics, we estimate that 94 million to 220 million people are potentially exposed to high arsenic concentrations in groundwater, the vast majority (94%) being in Asia. Because groundwater is increasingly used to support growing populations and buffer against water scarcity due to changing climate, this work is important to raise awareness, identify areas for safe wells, and help prioritize testing.