Snowpack levels across a wide swath of western US states are among the lowest seen in decades, even as regulators struggle to negotiate water rights in the region. States across the western US are facing record low snowpack levels in the middle of the winter season. The snowpack crisis, which could mean a drier, more wildfire -prone summer, is coming as states are racing unsuccessfully against a deadline to agree on terms to share water in the Colorado River Basin, the source of water for 40 million people across seven states in the West. "Barring a genuinely miraculous turnaround" in the remainder of the winter, says Daniel Swain, a climate scientist at the University of California Agriculture and Natural Resources, the low snowpack "has the potential to worsen both the ecological and political crisis on the Colorado Basin, and then also produce really adverse wildfire conditions in some parts of the West." Data provided by the US Department of Agriculture show that as of February 12, snowpack was at less than half its normal level in areas across nine Western states--some of the lowest levels seen in decades.

In this work, we propose a first approach and benchmarks to tackle this challenge.

Drought poses a pervasive environmental challenge in Bangladesh, impacting agriculture, socio-economic stability, and food security due to its unique geographic and anthropogenic vulnerabilities. Traditional drought indices, such as the Standardized Precipitation Index (SPI) and Palmer Drought Severity Index (PDSI), often overlook crucial factors like soil moisture and temperature, limiting their resolution. Moreover, current machine learning models applied to drought prediction have been underexplored in the context of Bangladesh, lacking a comprehensive integration of satellite data across multiple districts. To address these gaps, we propose a satellite data-driven machine learning framework to classify drought across 38 districts of Bangladesh. Using unsupervised algorithms like K-means and Bayesian Gaussian Mixture for clustering, followed by classification models such as KNN, Random Forest, Decision Tree, and Naive Bayes, the framework integrates weather data (humidity, soil moisture, temperature) from 2012-2024. This approach successfully classifies drought severity into different levels. However, it shows significant variabilities in drought vulnerabilities across regions which highlights the aptitude of machine learning models in terms of identifying and predicting drought conditions.

When clothing designers place an order at Katty Fashion's factory in Iași, Romania, they expect a bespoke service. If necessary, the factory will even rejig its production lines to make whichever garment a designer commissions. "From order to order, we may have to adapt," says Eduard Modreanu, the company's technical lead. "We cannot create one production line or shop floor that fits everyone." This adaptability is useful given the many diverse clients and orders Katty Fashion juggles, but it could also help future-proof the company against climate shocks.

Reliable forecasting is critical for early warning systems and adaptive drought management. Most previous deep learning approaches focus solely on homogeneous regions and rely on single-structured data. This paper presents a hybrid neural architecture that integrates time series and static data, achieving state-of-the-art performance on the DroughtED dataset. Our results illustrate the potential of designing neural models for the treatment of heterogeneous data in climate related tasks and present reliable prediction of USDM categories, an expert-informed drought metric. Furthermore, this work validates the potential of DroughtED for enabling location-agnostic training of deep learning models.

Anyone who has tried to keep porch plants or a home garden alive through seasonal changes knows it's a task easier said than done. Abrupt temperature changes--like cold snaps--and prolonged periods of drought can stress plants, disrupting their normal biochemistry. If not addressed quickly enough, those stresses can eventually kill the plant. Disappointed growers often only see the tell-tale signs (like shriveling or browning leaves) after it's too late. But a new plant-wearable device developed by researchers at the American Chemical Society could offer an early warning system. The wearable, detailed this week in the journal ACS Sensors, comes in the form of an electromagnetic sensor attached directly to plant leaves.

Drought is a frequent and costly natural disaster in California, with major negative impacts on agricultural production and water resource availability, particularly groundwater. This study investigated the performance of applying different machine learning approaches to predicting the U.S. Drought Monitor classification in California. Four approaches were used: a convolutional neural network (CNN), random forest, XGBoost, and long short term memory (LSTM) recurrent neural network, and compared to a baseline persistence model. We evaluated the models' performance in predicting severe drought (USDM drought category D2 or higher) using a macro F1 binary classification metric. The LSTM model emerged as the top performer, followed by XGBoost, CNN, and random forest. Further evaluation of our results at the county level suggested that the LSTM model would perform best in counties with more consistent drought patterns and where severe drought was more common, and the LSTM model would perform worse where drought scores increased rapidly. Utilizing 30 weeks of historical data, the LSTM model successfully forecasted drought scores for a 12-week period with a Mean Absolute Error (MAE) of 0.33, equivalent to less than half a drought category on a scale of 0 to 5. Additionally, the LSTM achieved a macro F1 score of 0.9, indicating high accuracy in binary classification for severe drought conditions. Evaluation of different window and future horizon sizes in weeks suggested that at least 24 weeks of data would result in the best performance, with best performance for shorter horizon sizes, particularly less than eight weeks.

From Snowpiercer to The Day After Tomorrow, countless movies and series have put forward their vision of how climate change might reshape the world. Worryingly, scientists predict that the reality might be far more shocking than anything imagined by a Hollywood studio. Now, artificial intelligence (AI) reveals what this might look like. With Google's ImageFX AI image generator, MailOnline has used the latest scientific research to predict how the world will be in 2100. As greenhouse gas levels continue to increase, scientists predict that entire cities will be plunged under water.

Drought is one of the most destructive and expensive natural disasters, severely impacting natural resources and risks by depleting water resources and diminishing agricultural yields. Under climate change, accurately predicting drought is critical for mitigating drought-induced risks. However, the intricate interplay among the physical and biological drivers that regulate droughts limits the predictability and understanding of drought, particularly at a subseasonal to seasonal (S2S) time scale. While deep learning has been demonstrated with potential in addressing climate forecasting challenges, its application to drought prediction has received relatively less attention. In this work, we propose a new dataset, DroughtSet, which integrates relevant predictive features and three drought indices from multiple remote sensing and reanalysis datasets across the contiguous United States (CONUS). DroughtSet specifically provides the machine learning community with a new real-world dataset to benchmark drought prediction models and more generally, time-series forecasting methods. Furthermore, we propose a spatial-temporal model SPDrought to predict and interpret S2S droughts. Our model learns from the spatial and temporal information of physical and biological features to predict three types of droughts simultaneously. Multiple strategies are employed to quantify the importance of physical and biological features for drought prediction. Our results provide insights for researchers to better understand the predictability and sensitivity of drought to biological and physical conditions. We aim to contribute to the climate field by proposing a new tool to predict and understand the occurrence of droughts and provide the AI community with a new benchmark to study deep learning applications in climate science.