Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of human activities and climate change. This study investigates the performance of deep learning models, particularly the Transformer model, as there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, a commonly used indicator of phytoplankton biomass and a proxy for HAB occurrences, is used as the target variable. We consider multiple influencing parameters—including physical, chemical, and biological water quality monitoring data from multiple stations located west of Lake Erie—and employ SHapley Additive exPlanations (SHAP) values as an explainable artificial intelligence (XAI) tool to identify key input features affecting HABs. Our findings highlight the superiority of deep learning models, especially the Transformer, in capturing the complex dynamics of water quality parameters and providing actionable insights for ecological management. The SHAP analysis identifies Particulate Organic Carbon, Particulate Organic Nitrogen, and total phosphorus as critical factors influencing HAB predictions. This study contributes to the development of advanced predictive models for HABs, aiding in early detection and proactive management strategies.
1 October 2024 in Environmental Research Communications
Hydrometeorological disasters, including floods and droughts, have intensified in both frequency and severity in recent years. This trend underscores the critical role of timely monitoring, accurate forecasting, and effective warning systems in facilitating proactive responses. Today’s information systems offer a vast and intricate mesh of data, encompassing satellite imagery, meteorological metrics, and predictive modeling. Easily accessible to the general public, these cyberinfrastructures simulate potential disaster scenarios, serving as invaluable aids to decision-making processes. This review collates key literature on water-related disaster information systems, underscoring the transformative impact of emerging information and Internet technologies. These advancements promise enhanced flood and drought warning timeliness and greater preparedness through improved management, analysis, visualization, and data sharing. Moreover, these systems aid in hydrometeorological predictions, foster the development of web-based educational platforms, and support decision-making frameworks, digital twins, and metaverse applications in disaster contexts. They further bolster scientific research and development, enrich climate change vulnerability frameworks, and strengthen associated cyberinfrastructures. This article delves into prospective developments in the realm of natural disasters, pinpointing primary challenges and gaps in current water-related disaster information systems, and highlighting the potential intersections with future artificial intelligence solutions.
25 March 2017 in Meteorology and Atmospheric Physics
Big data generated by remote sensing, ground-based measurements, models and simulations, social media and crowdsourcing, and a wide range of structured and unstructured sources necessitates significant data and knowledge management efforts. Innovations and developments in information technology over the last couple of decades have made data and knowledge management possible for an insurmountable amount of data collected and generated over the last decades. This enabled open knowledge networks to be built that led to new ideas in scientific research and the business world. To design and develop open knowledge networks, ontologies are essential since they form the backbone of conceptualization of a given knowledge domain. A systematic literature review was conducted to examine research involving ontologies related to hydrological processes and water resource management. Ontologies in the hydrology domain support the comprehension, monitoring, and representation of the hydrologic cycle’s complex structure, as well as the predictions of its processes. They contribute to the development of ontology-based information and decision support systems; understanding of environmental and atmospheric phenomena; development of climate and water resiliency concepts; creation of educational tools with artificial intelligence; and strengthening of related cyberinfrastructures. This review provides an explanation of key issues and challenges in ontology development based on hydrologic processes to guide the development of next generation artificial intelligence applications. The study also discusses future research prospects in combination with artificial intelligence and hydroscience.
The significance of improving rainfall prediction methods has escalated due to climate change-induced flash floods and severe flooding. In this study, rainfall nowcasting has been studied utilizing NASA Giovanni satellite-derived precipitation products and the convolutional long short-term memory (ConvLSTM) approach. The goal of the study is to assess the impact of data augmentation on flood nowcasting. Due to data requirements of deep learning-based prediction methods, data augmentation is performed using eight different interpolation techniques. Spatial, temporal, and spatio-temporal interpolated rainfall data are used to conduct a comparative analysis of the results obtained through nowcasting rainfall. This research examines two catastrophic floods that transpired in Türkiye Marmara Region in 2009 and the Central Black Sea Region in 2021, which are selected as the focal case studies. The Marmara and Black Sea regions are prone to frequent flooding, which, due to the dense population, has devastating consequences. Furthermore, these regions exhibit distinct topographical characteristics and precipitation patterns, and the frontal systems that impact them are also dissimilar. The nowcast results for the two regions exhibit a significant difference. Although data augmentation significantly reduced the error values by 59% for one region, it did not yield the same effectiveness for the other region.