Tingting Xu , Aohua Tian , Jay Gao , Haoze Yan , Chang Liu
{"title":"Analysis of the spatial heterogeneity of glacier melting in Tibet Autonomous Region and its influential factors using the K-means and XGBoost-SHAP algorithms","authors":"Tingting Xu , Aohua Tian , Jay Gao , Haoze Yan , Chang Liu","doi":"10.1016/j.envsoft.2024.106194","DOIUrl":"10.1016/j.envsoft.2024.106194","url":null,"abstract":"<div><p>This study employed machine learning to comprehensively analyze glacier melting in Tibet Autonomous Region (TAR) and its vital influencing factors. Existing machine learning research often lacks detailed explanations, leading to generalized predictions without considering essential driving factors necessary for yielding an insightful understanding of glacier melting dynamics. To overcome these limitations and fulfill multi-level analysis requirements for comprehending glacier melting, this study identifies factors contributing to glacier melting heterogeneity and assesses distinct melting causes in three spatial melted glacier clusters. We utilized K-means unsupervised classification to cluster Tibet melted glaciers into three categories based on temperature, sunshine hours, evapotranspiration, precipitation, normalized vegetation index, and slope. XGBoost algorithm explores the nonlinear relationships of glacier melting with these features and Shapley values were used for model transparency, quantifying feature's influence on the melting process. Investigating geographical heterogeneity among clusters enhanced our understanding of the observed changes. High fitting accuracy (>0.98) enhanced the result reliability, as well. The results show that Tibetan glaciers melt significantly from 2010 to 2020, and the cluster analysis reveals its unique melting characteristics. Melting glaciers in the same cluster are not only similar in characteristics, but also in spatial and geographical distribution, with two of the clusters concentrating in the eastern part of TAR, and the third cluster scattered in the western part of the country. the XGBoost-SHAP analysis efficiently quantifies the contribution of each cluster feature to the glacier melting, revealing the different roles of different clustered features.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"182 ","pages":"Article 106194"},"PeriodicalIF":4.8,"publicationDate":"2024-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144027","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}
Xuelei Zhang , Hu Yang , Chunhua Liu , Qingqing Tong , Aijun Xiu , Lingsheng Kong , Mo Dan , Chao Gao , Meng Gao , Huizheng Che , Xin Wang , Guangjian Wu
{"title":"XR-based interactive visualization platform for real-time exploring dynamic earth science data","authors":"Xuelei Zhang , Hu Yang , Chunhua Liu , Qingqing Tong , Aijun Xiu , Lingsheng Kong , Mo Dan , Chao Gao , Meng Gao , Huizheng Che , Xin Wang , Guangjian Wu","doi":"10.1016/j.envsoft.2024.106193","DOIUrl":"10.1016/j.envsoft.2024.106193","url":null,"abstract":"<div><p>The transition from 2D planar displays to immersive holographic 3D environments has brought advancements in visualization technology. However, there remains a lack of effective interactive visualization tools for complex multi-dimensional structured or unstructured datasets in immersive space. To address this gap, we have developed MetIVA, a state-of-the-art multiscale interactive data visualization platform that leverages the Extended Reality (XR) and cloud rendering technology for immersive data exploration. In this paper, we firstly outline the historical development of scientific visualization and the recent shift towards 3D and higher-dimensional visualization, and then basically introduce the conceptual framework and platform structure of MetIVA, and finally present the evaluation results from recruited potential users. The results confirm that MetIVA is a powerful tool to accelerate data exploration and decision-making processes. Its interactive and intuitive features, along with ongoing optimization efforts, make it a valuable tool for researchers and practitioners in the field of Earth science.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"183 ","pages":"Article 106193"},"PeriodicalIF":4.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142158419","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}
Madeline E. Scyphers , Justine E.C. Missik , Haley Kujawa , Joel A. Paulson , Gil Bohrer
{"title":"Bayesian Optimization for Anything (BOA): An open-source framework for accessible, user-friendly Bayesian optimization","authors":"Madeline E. Scyphers , Justine E.C. Missik , Haley Kujawa , Joel A. Paulson , Gil Bohrer","doi":"10.1016/j.envsoft.2024.106191","DOIUrl":"10.1016/j.envsoft.2024.106191","url":null,"abstract":"<div><p>We introduce Bayesian Optimization for Anything (BOA), a high-level Bayesian Optimization (BO) framework and model wrapping toolkit, which presents a novel approach to simplifying BO, with the goal of making it more accessible and user-friendly, particularly for those with limited expertise in the field. BOA addresses common barriers in implementing BO, focusing on ease of use, reducing the need for deep domain knowledge, and cutting down on extensive coding requirements. A notable feature of BOA is its language-agnostic architecture, which facilitates broader application in various fields and to a wider audience. We showcase BOA's application through three examples: a high-dimensional optimization with 184 parameters of the SWAT + watershed model, a highly parallelized optimization of this intrinsically non-parallel model, and a multi-objective optimization of the FETCH Tree-Crown Hydrodynamics model. These test cases illustrate BOA's effectiveness in addressing complex optimization challenges in diverse scenarios.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"182 ","pages":"Article 106191"},"PeriodicalIF":4.8,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142101385","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}
{"title":"ForestAdvisor: A multi-modal forest decision-making system based on carbon emissions","authors":"Tong Ji , Yifeng Lin , Yuer Yang","doi":"10.1016/j.envsoft.2024.106190","DOIUrl":"10.1016/j.envsoft.2024.106190","url":null,"abstract":"<div><p>Effectively balancing carbon emission reduction with economic viability through regional forest management is a significant challenge for global ecosystems. This paper introduces an innovative multi-modal forest decision-making system, integrating deep learning and natural language processing technologies, aimed at optimizing forest management strategies. Experimental validation of this system was conducted in three distinct forested regions. Utilizing a deep learning model, the system analyzed and predicted daily carbon emissions data. The experiments demonstrated remarkable accuracy, with the model achieving a coefficient of determination (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>) of up to 0.94, 0.98, and 0.99 across datasets from all three regions, thereby justifying its use for forecasting carbon emission trends over the following months. Subsequently, the system employed natural language processing to assess the importance of various collected forest management strategies. Finally, the system fine-tuned these strategy combinations in response to the predicted carbon emission trends, ensuring flexibility and effectiveness in addressing the complex dynamics of carbon emission fluctuations.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106190"},"PeriodicalIF":4.8,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142077006","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}
Lu Wang , Yue-Ping Xu , Jiliang Xu , Haiting Gu , Zhixu Bai , Peng Zhou , Hongjie Yu , Yuxue Guo
{"title":"Increasing parameter identifiability through clustered time-varying sensitivity analysis","authors":"Lu Wang , Yue-Ping Xu , Jiliang Xu , Haiting Gu , Zhixu Bai , Peng Zhou , Hongjie Yu , Yuxue Guo","doi":"10.1016/j.envsoft.2024.106189","DOIUrl":"10.1016/j.envsoft.2024.106189","url":null,"abstract":"<div><p>Hydrological models are becoming progressively complex, leading to unclear internal model behavior, increasing uncertainty, and the risk of equifinality. Accordingly, our study provided a research framework based on global sensitivity analysis, aiming at unraveling the process-level behavior of high-complexity models, teasing out the main information, and ultimately exploiting its usage for model parameterization. The Distributed Hydrology-Soil-Vegetation Model implemented in a mountainous watershed was used. Results indicated that 5 soil parameters and 5 vegetation parameters were most important to control the streamflow responses, while their importance varied greatly throughout the simulation period. Four typical patterns of parameter importance corresponding to different watershed conditions (i.e., flood, short dry-to-wet, fast recession, and continuous dry periods) were successfully distinguished. Using this clustered information, parameters with short dominance times were more identifiable over the clusters (time periods) in which they were most important. The reduced posterior parameter space also slightly improved the model performance.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106189"},"PeriodicalIF":4.8,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047903","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}
Laura Müller , Max Czymai , Birgit Blättel-Mink , Petra Döll
{"title":"How to assess conditions for the acceptance of climate change adaptation measures by applying implementation probability Bayesian Networks in participatory processes","authors":"Laura Müller , Max Czymai , Birgit Blättel-Mink , Petra Döll","doi":"10.1016/j.envsoft.2024.106188","DOIUrl":"10.1016/j.envsoft.2024.106188","url":null,"abstract":"<div><p>Climate change adaptation measures are best identified participatorily, yet their implementation poses challenges. While Bayesian Network (BN) modeling has been widely used to assess how adaptation measures mitigate risks, we present how to develop, in a participatory process, an innovative BN type that quantifies the implementation probability of adaptation measures by considering conditions for actors’ acceptance as well as cultural worldviews. The BN structure was derived from participatorily identified causal networks, while the conditional probability tables were straightforwardly developed with stakeholder-assigned weights. Sensitivity analysis shows how BN structure and parameters influence the BN results. We found that our approach achieves knowledge integration and learning without overwhelming stakeholders with technical details. As BNs enable exploring scenarios, stakeholders learn that many plausible futures exist. Integrating our approach in participatory adaptation processes contributes to identifying the best combinations of implementation actions, reducing the “know-do gap” in local adaptation challenges.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106188"},"PeriodicalIF":4.8,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224002494/pdfft?md5=dea53c061631a1c69c03572d58c0e5a2&pid=1-s2.0-S1364815224002494-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142088855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chung-Yi Lin , Maria Elena Orduna Alegria , Sameer Dhakal , Sam Zipper , Landon Marston
{"title":"PyCHAMP: A crop-hydrological-agent modeling platform for groundwater management","authors":"Chung-Yi Lin , Maria Elena Orduna Alegria , Sameer Dhakal , Sam Zipper , Landon Marston","doi":"10.1016/j.envsoft.2024.106187","DOIUrl":"10.1016/j.envsoft.2024.106187","url":null,"abstract":"<div><p>The Crop-Hydrological-Agent Modeling Platform (PyCHAMP) is a Python-based open-source package designed for modeling agro-hydrological systems. The modular design, incorporating aquifer, crop field, groundwater well, finance, and behavior components, enables users to simulate and analyze the interactions between human and natural systems, considering both environmental and socio-economic factors. This study demonstrates PyCHAMP's capabilities by simulating the dynamics in the Sheridan 6 Local Enhanced Management Area, a groundwater conservation program in the High Plains Aquifer in Kansas. We highlight how a model, empowered by PyCHAMP, accurately captures human-water dynamics, including groundwater level, water withdrawal, and the fraction of cropland dedicated to each crop. We also show how farmer behavior, and its representation, drives system outcomes more strongly than environmental conditions. The results indicate PyCHAMP's potential as a useful tool for human-water research and sustainable groundwater management, offering prospects for future integration with detailed sub-models and systematic evaluation of model structural uncertainty.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106187"},"PeriodicalIF":4.8,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141985253","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}
W. Matt Jolly , Patrick H. Freeborn , Larry S. Bradshaw , Jon Wallace , Stuart Brittain
{"title":"Modernizing the US National Fire Danger Rating System (version 4): Simplified fuel models and improved live and dead fuel moisture calculations","authors":"W. Matt Jolly , Patrick H. Freeborn , Larry S. Bradshaw , Jon Wallace , Stuart Brittain","doi":"10.1016/j.envsoft.2024.106181","DOIUrl":"10.1016/j.envsoft.2024.106181","url":null,"abstract":"<div><p>The US National Fire Danger Rating System (USNFDRS) supports wildfire management decisions nationwide, but it has not been updated since 1988. Here we implement new fuel moisture models, and we simplify the fuel models while maintaining the overall USNFDRS structure. Modeled and measured live fuel moisture content values were highly correlated (<span><math><mrow><msup><mrow><mi>r</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>629</mn></mrow></math></span> with defaults and <span><math><mrow><msup><mrow><mi>r</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>693</mn></mrow></math></span> when species and location optimized). We also consolidated fuel models to five fuel types that eliminated significant index cross-correlation. Index seasonality compared between old (V2) and new USNFDRS models (v4) across six US National Forests was very similar (<span><math><mrow><mi>ρ</mi><mo>=</mo></mrow></math></span> 0.97). V4 was as good or better than V2 at predicting fire days in 92% of the cases tested and V4 effectively predicted wildfire days and large fire ignition days (AUCs 0.647 to 0.915). USNFDRS V4 can adequately depict spatial and temporal wildland fire potential and it can be adapted for worldwide use.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106181"},"PeriodicalIF":4.8,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224002421/pdfft?md5=0bad9d72fff3df2a680583db6650ac7a&pid=1-s2.0-S1364815224002421-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142047904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hui Zou , Lucy Marshall , Ashish Sharma , Jie Jian , Clare Stephens , Philippa Higgins
{"title":"Modelling vegetation dynamics for future climates in Australian catchments: Comparison of a conceptual eco-hydrological modelling approach with a deep learning alternative","authors":"Hui Zou , Lucy Marshall , Ashish Sharma , Jie Jian , Clare Stephens , Philippa Higgins","doi":"10.1016/j.envsoft.2024.106179","DOIUrl":"10.1016/j.envsoft.2024.106179","url":null,"abstract":"<div><p>Dynamically simulating leaf area index assists in modelling the feedbacks between eco-hydrologic and climatic processes. The particular challenge for Australia is the prevalence of arid and semi-arid ecosystems where water availability plays a crucial role in vegetation productivity. To understand whether existing LAI models can capture plant dynamics under changing climates, we tested two competing models across Australia's different climate zones: a conceptual eco-hydrologic model that applies water use efficiency term to relate LAI to water uptake, and a deep learning approach. An initial virtual catchment experiment with deep learning showed that it only uses information from potential evapotranspiration. For future climates, the conceptual model captured a negative trend and increasing variance in LAI, which is plausible given projected rainfall changes, while deep learning did not. Our study demonstrated an example of ‘right answer for the wrong reasons’, and the importance of incorporating knowledge of water-carbon coupling for appropriate scenarios.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106179"},"PeriodicalIF":4.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224002408/pdfft?md5=a17aa7bf042ec562a0e4f5935767b5b9&pid=1-s2.0-S1364815224002408-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142043584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Web application of an integrated simulation for aquatic environment assessment in coastal and estuarine areas","authors":"Yoshitaka Matsuzaki , Tetsunori Inoue , Masaya Kubota , Hiroki Matsumoto , Tomoyuki Sato , Hikari Sakamoto , Daisuke Naito","doi":"10.1016/j.envsoft.2024.106184","DOIUrl":"10.1016/j.envsoft.2024.106184","url":null,"abstract":"<div><p>This paper introduces the web application-type Graphical User Interface that has been developed and also presents an application example. The introduced simulator conducts hydrodynamics and ecosystems in coastal and estuarine areas. It consists of (1) a hydrodynamic model that can simulate the current velocity, water temperature, salinity, and water level; (2) an ecosystem model that can simulate dissolved oxygen, phytoplankton, zooplankton, nutrients, fish, and bivalves; and (3) a benthic ecosystem model that can simulate elution. Web GUI is the first web system of aquatic environment simulation system that can both prepare calculation conditions and visualize them. Another significant feature is that it requires no installation and can be easily used by anyone to perform calculations. Thus, the proposed system helps fill the expertise gap experienced by potential users of the model. The use of standard systems, such as those discussed in this study, will facilitate evidence-based policymaking (EBPM).</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":"181 ","pages":"Article 106184"},"PeriodicalIF":4.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224002457/pdfft?md5=50affda9fd41d1b57556dae1043a0eff&pid=1-s2.0-S1364815224002457-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142077005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}