Environmental Modelling & Software最新文献_第9页

How to use general AI for task-specific applications: A case study of monitoring water level trends with river cameras 如何将通用人工智能用于特定任务应用：用河流摄像机监测水位趋势的案例研究

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-28 DOI: 10.1016/j.envsoft.2025.106550

Ze Wang , Heng Lyu , Yanqing Guo , Shun'an Zhou , Chi Zhang

{"title":"How to use general AI for task-specific applications: A case study of monitoring water level trends with river cameras","authors":"Ze Wang , Heng Lyu , Yanqing Guo , Shun'an Zhou , Chi Zhang","doi":"10.1016/j.envsoft.2025.106550","DOIUrl":"10.1016/j.envsoft.2025.106550","url":null,"abstract":"<div><div>Water level variations influence geochemical and hydrological processes within river networks. Water segmentation from river camera images using deep learning supports water level trend monitoring, but domain-specific model accuracies are constrained by limited annotated data. To improve accuracy, this study proposes a framework combining domain-specific models with General AI. The framework uses the Segment Anything Model (SAM) as backbone, with a pre-trained ResUnet model identifying highest-probability water pixels as a prompt to SAM, without any requirement for human intervention or local annotation. Applied to river camera images from Tewkesbury, UK, the framework increased the Intersection over Union (<em>IoU</em>) by over 15 % compared to the single ResUnet. <em>Point prompt</em> was identified as the optimal mode for feeding water-related prior knowledge to SAM. The static observer flooding index derived from segmented masks showed a strong correlation (0.90) with real water level, surpassing the ResUnet's 0.54. Our framework allows for the supplementation of river monitoring networks with camera gauges, providing robust water level trend observations.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106550"},"PeriodicalIF":4.8,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144189609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting climate change: A comparative analysis of time series models for CO2 concentrations and temperature anomalies 预测气候变化：CO2浓度和温度异常的时间序列模式的比较分析

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-26 DOI: 10.1016/j.envsoft.2025.106533

Zahra Rezaei , Sara Safi Samghabadi , Mohammad Amin Amini , Dingjing Shi , Yaser Mike Banad

{"title":"Predicting climate change: A comparative analysis of time series models for CO2 concentrations and temperature anomalies","authors":"Zahra Rezaei , Sara Safi Samghabadi , Mohammad Amin Amini , Dingjing Shi , Yaser Mike Banad","doi":"10.1016/j.envsoft.2025.106533","DOIUrl":"10.1016/j.envsoft.2025.106533","url":null,"abstract":"<div><div>This study presents a novel, integrated modeling framework that combines machine learning (ML) techniques with physics-based approaches to forecast both CO<sub>2</sub> emissions and global temperature anomalies. Unlike prior research that typically addresses these components in isolation, this work concurrently applies and compares five advanced ML models—Long Short-Term Memory (LSTM), Extreme Gradient Boosting (XGBoost), Convolutional Neural Network (CNN), Facebook Prophet, and a hybrid CNN-LSTM—alongside two physics-based models: a zero-dimensional Energy Balance Model (EBM) and a simplified General Circulation Model (GCM) adapted from NASA's GISS framework.Using monthly global datasets from January 2000 to April 2024, obtained from the National Oceanic and Atmospheric Administration (NOAA) and the Scripps Institution of Oceanography, the models are evaluated based on predictive accuracy (RMSE, MSE, MAE, R<sup>2</sup>), scalability, and interpretability. Prophet demonstrated the highest accuracy for CO<sub>2</sub> emission forecasting (RMSE = 0.035), while LSTM achieved the best performance in temperature anomaly prediction (RMSE = 0.086). Physics-based models provided interpretable and computationally efficient long-term projections but lacked short-term flexibility.To facilitate reproducibility and practical application, we developed ClimateChange-ML, an open-source software package that implements all proposed models, includes trained weights, and provides full documentation and visualization tools.The novelty of this work lies in its dual-modeling strategy and comprehensive comparative evaluation, highlighting the complementary strengths of data-driven and physically grounded methods. This integrated approach offers a more holistic framework for climate forecasting across multiple temporal scales, providing valuable insights for both scientific understanding and climate policy planning.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106533"},"PeriodicalIF":4.8,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Climate change impacts on solar energy generation in the continental United States, forecasts from deep learning 气候变化对美国大陆太阳能发电的影响，深度学习预测

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-24 DOI: 10.1016/j.envsoft.2025.106535

Cody Nichols, Mary Hill, Xuebo Liu, Lawryn Kiboma

{"title":"Climate change impacts on solar energy generation in the continental United States, forecasts from deep learning","authors":"Cody Nichols, Mary Hill, Xuebo Liu, Lawryn Kiboma","doi":"10.1016/j.envsoft.2025.106535","DOIUrl":"10.1016/j.envsoft.2025.106535","url":null,"abstract":"<div><div>Large-scale solar promises a low-carbon energy alternative. However, solar production in North America given anticipated climate change has been studied only seasonally in terms of solar irradiance. This work integrates more of the predictive potential of climate-change models by exploring other environmental variables, such as humidity and temperature. Here, a Continental US (CONUS) model is produced by deep learning using 2593 NREL simulated solar power stations. Daily forecasts using 17 Global Climate Models (GCM's) through 2099 are summarized monthly. Results suggest power production factors change between +4 % and −19 % over 93 years. These results suggest more, but still modest, potential declines than previous solar irradiance-based studies. The modest impact is encouraging. For some areas, climate model variability unfortunately yielded statistically insignificant trends and practical application is less clear. For future evaluations, this work suggests the potential importance of additional variables, monthly interval summary, and accounting for model variability.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106535"},"PeriodicalIF":4.8,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144184180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ice-jam flood predictions using an interpretable machine learning approach 使用可解释的机器学习方法进行冰堵塞洪水预测

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-23 DOI: 10.1016/j.envsoft.2025.106534

Ananya Kowshal , Apurba Das , Karl-Erich Lindenschmidt

引用次数: 0

Harnessing Twitter (X) with AI-enhanced natural language processing for disaster management: Insights from California wildfire 利用Twitter (X)与人工智能增强的自然语言处理进行灾害管理：来自加州野火的见解

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-23 DOI: 10.1016/j.envsoft.2025.106545

Mohammadsepehr Karimiziarani, Ehsan Foroumandi, Hamid Moradkhani

{"title":"Harnessing Twitter (X) with AI-enhanced natural language processing for disaster management: Insights from California wildfire","authors":"Mohammadsepehr Karimiziarani, Ehsan Foroumandi, Hamid Moradkhani","doi":"10.1016/j.envsoft.2025.106545","DOIUrl":"10.1016/j.envsoft.2025.106545","url":null,"abstract":"<div><div>Social media usage surges during natural disasters, offering critical insights into public sentiment and needs. This study leverages artificial intelligence (AI) and advanced natural language processing (NLP) techniques to analyze Twitter (X) data from the 2018 California Camp Fire. By combining sentiment analysis, emotion classification, and humanitarian topic classification, we provide a nuanced understanding of social responses. Tweets were categorized into six humanitarian topics and twelve emotion classes, revealing significant regional and temporal variations. Our findings show shifts from immediate safety concerns to recovery and support as the disaster progressed. Results highlight key differences in emotional responses between California and other U.S. states, emphasizing the role of proximity in shaping social media discourse. These AI-driven insights can inform disaster management strategies by optimizing communication, resource allocation, and real-time decision-making. This research underscores the value of AI-powered social media analysis in enhancing disaster preparedness, response, and recovery efforts.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106545"},"PeriodicalIF":4.8,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unveiling uncertainties in soil organic carbon modeling: the critical role of climate response functions 揭示土壤有机碳模型中的不确定性：气候响应函数的关键作用

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-22 DOI: 10.1016/j.envsoft.2025.106537

Huiwen Li , Yue Cao , Jingfeng Xiao , Wenxin Zhang , Yiping Wu , Arshad Ali , Zuoqiang Yuan

{"title":"Unveiling uncertainties in soil organic carbon modeling: the critical role of climate response functions","authors":"Huiwen Li , Yue Cao , Jingfeng Xiao , Wenxin Zhang , Yiping Wu , Arshad Ali , Zuoqiang Yuan","doi":"10.1016/j.envsoft.2025.106537","DOIUrl":"10.1016/j.envsoft.2025.106537","url":null,"abstract":"<div><div>Accurately simulating soil organic carbon (SOC) dynamics is essential for carbon-related assessments. Process-oriented SOC models employ temperature (<em>f</em>(T)) and soil moisture (<em>f</em>(W)) response functions derived from specific conditions to simulate SOC responses to climate change, yet are widely applied in regional and global-scale studies. How these functions affect regional SOC simulations remains unclear. We evaluated the impacts of ten <em>f</em>(T) and nine <em>f</em>(W) functions using the Double Layer Carbon Model (DLCM) in the Qinling Mountains from 1982 to 2018. After calibration by Particle Swarm Optimization, DLCM estimated initial SOC with high spatial consistency (<em>R</em><sup>2</sup> > 0.9) and less than 1 % bias against machine learning based baseline maps over 85 % of the area. Different functions led to large SOC variations (up to 37 % in topsoil and 30 % in subsoil). Their combined impacts vary significantly under climate fluctuations, highlighting the need for accurate functions to improve SOC prediction in a changing climate.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106537"},"PeriodicalIF":4.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigate the rainfall-runoff relationship and hydrological concepts inside LSTM 研究降雨径流关系和LSTM内部的水文概念

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-22 DOI: 10.1016/j.envsoft.2025.106527

Yuqian Hu , Heng Li , Chunxiao Zhang , Tianbao Wang , Wenhao Chu , Rongrong Li

{"title":"Investigate the rainfall-runoff relationship and hydrological concepts inside LSTM","authors":"Yuqian Hu , Heng Li , Chunxiao Zhang , Tianbao Wang , Wenhao Chu , Rongrong Li","doi":"10.1016/j.envsoft.2025.106527","DOIUrl":"10.1016/j.envsoft.2025.106527","url":null,"abstract":"<div><div>Recent studies have shown that LSTM performs well in runoff prediction in large sample regional modeling and can estimate hydrological concepts based on its internal information. However, compared to process-based models, it still produces erroneous predictions that violate the physical laws. To explore the reasons for the above phenomenon, this study analyzes the evolution of LSTM's performance in predicting runoff and estimating hydrological concepts when trained on a large basinscale dataset. Findings demonstrated that LSTM's representation of the rainfall-runoff relationship lags behind the formation of hydrological concepts. The representations of relations and concepts do not consistently increase with the number of training basins. There is a model that achieves the best representation of the rainfall-runoff relationship and hydrological concepts, ensuring physical consistency even under extreme conditions. These results suggest that LSTM, like process-based models, learns the rainfall-runoff relationship and hydrological concepts, but its confusion about these concepts may lead to inaccurate predictions.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106527"},"PeriodicalIF":4.8,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling wildfire dynamics through a physics-based approach incorporating fuel moisture and landscape heterogeneity 通过结合燃料湿度和景观异质性的基于物理的方法模拟野火动力学

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-22 DOI: 10.1016/j.envsoft.2025.106511

Adrián Navas-Montilla , Cordula Reisch , Pablo Diaz , Ilhan Özgen-Xian

引用次数: 0

DigiAgriApp: a client-server application to monitor field activities DigiAgriApp：监控现场活动的客户机-服务器应用程序

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-19 DOI: 10.1016/j.envsoft.2025.106528

Marco Moretto , Luca Delucchi , Roberto Zorer , Damiano Moser , Franco Micheli , Andrea Paoli , Pietro Franceschi

{"title":"DigiAgriApp: a client-server application to monitor field activities","authors":"Marco Moretto , Luca Delucchi , Roberto Zorer , Damiano Moser , Franco Micheli , Andrea Paoli , Pietro Franceschi","doi":"10.1016/j.envsoft.2025.106528","DOIUrl":"10.1016/j.envsoft.2025.106528","url":null,"abstract":"<div><div>Farming is increasingly data-driven, leveraging high-frequency and precision data from IoT devices, sensors, and remote tools. Effective data collection, organization, and management are essential to link datasets with agronomic details, forming the foundation for predictive models. These models, using AI and machine learning, optimize decision-making, forecast crop yields, predict pest outbreaks, and enhance resource use. High-quality, diverse data integration is key to building accurate tools that address agriculture's complexity, boosting productivity and resilience. We introduce DigiAgriApp, an open-source client-server application for centralized farming data management. It tracks crop details, sensor readings, irrigation, field operations, production statistics, and emissions for Life Cycle Assessment. Initially developed for the Fondazione Edmund Mach, DigiAgriApp has evolved into a versatile tool. Users can access a public server or deploy a private instance via Docker, making it ideal for institutions, farmers, and corporations alike.</div><div>DigiAgriApp is available at <span><span>https://digiagriapp.gitlab.io/digiagriapp-website/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106528"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Position paper: Common mistakes and solutions for a better use of correlation- and regression-based approaches in environmental sciences 立场文件：在环境科学中更好地利用基于相关和回归的方法的常见错误和解决办法

IF 4.8 2区环境科学与生态学

Environmental Modelling & Software Pub Date : 2025-05-19 DOI: 10.1016/j.envsoft.2025.106526

Damien Tedoldi , Boram Kim , Santiago Sandoval , Nicolas Forquet , Bruno Tassin

{"title":"Position paper: Common mistakes and solutions for a better use of correlation- and regression-based approaches in environmental sciences","authors":"Damien Tedoldi , Boram Kim , Santiago Sandoval , Nicolas Forquet , Bruno Tassin","doi":"10.1016/j.envsoft.2025.106526","DOIUrl":"10.1016/j.envsoft.2025.106526","url":null,"abstract":"<div><div>While empirical modelling remains a popular practice in environmental sciences, an alarming number of misuses of correlation- and regression-based techniques are encountered in recent research, although these techniques are described in courses and textbooks. This position paper reviews the most common issues, and provides theoretical background for understanding the interests and limitations of these methods, based on their underlying assumptions. We call for a reconsideration of misleading practices, including: the application of linear regression to data points that do not display a linear pattern, the failure to pinpoint influential points, the inappropriate extrapolation of empirical relationships, the overrated search for “statistical significance”, the pooling of data belonging to different populations, and, most importantly, calculations without data visualization. We urge reviewers to be vigilant on these aspects. We also recall the existence of alternative approaches to overcome the highlighted shortcomings, and thus contribute to a more accurate interpretation of the results.</div></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"192 ","pages":"Article 106526"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144194031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0