Pub Date : 2024-07-02DOI: 10.1016/j.envsoft.2024.106133
Ayman H. Alzraiee , Richard G. Niswonger
Machine learning (ML) models are increasingly popular in environmental and hydrologic modeling, but they typically contain uncertainties resulting from noisy data (erroneous or outlier data). This paper presents a novel probabilistic approach that combines ML and Markov Chain Monte Carlo simulation to (1) detect and underweight likely noisy data, (2) develop an approach capable of detecting noisy data during model deployment, and (3) interpret the reasons why a data point is deemed noisy to help heuristically distinguish between outliers and erroneous data. The new algorithm recognizes that there is no unique way to split the training data into noisy and clean data, and thus produces an ensemble of plausible splits. The algorithm successfully detected noisy data in synthetic benchmark problems with varying complexity and a real-world public supply water withdrawal dataset. The algorithm is generic and flexible, making it suitable for application across a broad range of hydrologic and environmental disciplines.
机器学习(ML)模型在环境和水文建模中越来越受欢迎,但它们通常包含由噪声数据(错误或离群数据)导致的不确定性。本文介绍了一种新颖的概率方法,该方法结合了 ML 和马尔可夫链蒙特卡罗模拟,用于:(1)检测可能存在的噪声数据并降低其权重;(2)开发一种能够在模型部署过程中检测噪声数据的方法;以及(3)解释数据点被视为噪声的原因,以帮助启发式地区分异常值和错误数据。新算法认识到,将训练数据拆分为噪声数据和干净数据的方法并不唯一,因此会产生一系列合理的拆分。该算法在不同复杂度的合成基准问题和现实世界的公共供水取水数据集中成功检测出了噪声数据。该算法具有通用性和灵活性,适用于广泛的水文和环境学科。
{"title":"A probabilistic approach to training machine learning models using noisy data","authors":"Ayman H. Alzraiee , Richard G. Niswonger","doi":"10.1016/j.envsoft.2024.106133","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106133","url":null,"abstract":"<div><p>Machine learning (ML) models are increasingly popular in environmental and hydrologic modeling, but they typically contain uncertainties resulting from noisy data (erroneous or outlier data). This paper presents a novel probabilistic approach that combines ML and Markov Chain Monte Carlo simulation to (1) detect and underweight likely noisy data, (2) develop an approach capable of detecting noisy data during model deployment, and (3) interpret the reasons why a data point is deemed noisy to help heuristically distinguish between outliers and erroneous data. The new algorithm recognizes that there is no unique way to split the training data into noisy and clean data, and thus produces an ensemble of plausible splits. The algorithm successfully detected noisy data in synthetic benchmark problems with varying complexity and a real-world public supply water withdrawal dataset. The algorithm is generic and flexible, making it suitable for application across a broad range of hydrologic and environmental disciplines.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224001944/pdfft?md5=e1e87f0b5ef16de980acb3594e5d21d5&pid=1-s2.0-S1364815224001944-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141594469","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}
Pub Date : 2024-07-02DOI: 10.1016/j.envsoft.2024.106129
V.C. Manea , E.G. Sewell , M. Manea , S. Yoshioka , N. Suenaga , E.J. Moreno
A large number of bathymetric discontinuities mark the bottom of the oceans. Among these features, seamounts protruding the sedimentary layer can play a major role in establishing a continuous exchange of fluids and heat between the oceanic lithosphere and the ocean. Here we present finite element codes for calculating the flow, temperature and pressure distributions inside seamounts using a general-purpose finite element solver. We solve the coupled equations of continuity, Darcy equation, and energy conservation equation in 2-D. We present a numerical axisymmetrical model tailored to the real geometry of the Grizzly Bare seamount located on the Juan de Fuca plate. The surface heat flow shows a good correlation between our models and in-situ available observations. In this work we provide complete open access to numerical codes which are intended to be simple and easy to adapt for a wide range of seamounts shapes and sizes.
{"title":"Finite element software for calculating fluid flow and heat transport for seamounts","authors":"V.C. Manea , E.G. Sewell , M. Manea , S. Yoshioka , N. Suenaga , E.J. Moreno","doi":"10.1016/j.envsoft.2024.106129","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106129","url":null,"abstract":"<div><p>A large number of bathymetric discontinuities mark the bottom of the oceans. Among these features, seamounts protruding the sedimentary layer can play a major role in establishing a continuous exchange of fluids and heat between the oceanic lithosphere and the ocean. Here we present finite element codes for calculating the flow, temperature and pressure distributions inside seamounts using a general-purpose finite element solver. We solve the coupled equations of continuity, Darcy equation, and energy conservation equation in 2-D. We present a numerical axisymmetrical model tailored to the real geometry of the Grizzly Bare seamount located on the Juan de Fuca plate. The surface heat flow shows a good correlation between our models and in-situ available observations. In this work we provide complete open access to numerical codes which are intended to be simple and easy to adapt for a wide range of seamounts shapes and sizes.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224001907/pdfft?md5=52e21be2ca3aa08174790df04d6491eb&pid=1-s2.0-S1364815224001907-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141594471","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}
Pub Date : 2024-07-02DOI: 10.1016/j.envsoft.2024.106132
Vinh Ngoc Tran , Jongho Kim
The Urban Inundation-Drainage Simulator (UIDS) is a new coupled model for simulating urban flooding dynamics, developed as an open-source, MATLAB-based platform. It integrates a rainfall-runoff model with a two-dimensional overland flow model (OFM) and a one-dimensional sewer flow model (SFM). Unlike conventional models limited to either rainfall-induced or sewer surcharge-induced flooding, UIDS captures bidirectional surface-underground interactions to simulate both processes simultaneously. The OFM employs an explicit time-stepping scheme and robust wet-dry front treatment, while a weir equation describes roof-to-ground flow exchange for numerical stability. Timing synchronization facilitates continuous OFM-SFM coupling. Benchmarking and case studies of Gangnam flood events demonstrate UIDS's ability to accurately simulate urban flooding, particularly subcritical flows. The open-source nature of UIDS allows user flexibility in accessing and modifying the MATLAB code. Ultimately, UIDS is expected to serve as an accessible and adaptable tool for urban flood modeling and risk assessment.
{"title":"UIDS: A Matlab-based urban flood model considering rainfall-induced and surcharge-induced inundations","authors":"Vinh Ngoc Tran , Jongho Kim","doi":"10.1016/j.envsoft.2024.106132","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106132","url":null,"abstract":"<div><p>The Urban Inundation-Drainage Simulator (UIDS) is a new coupled model for simulating urban flooding dynamics, developed as an open-source, MATLAB-based platform. It integrates a rainfall-runoff model with a two-dimensional overland flow model (OFM) and a one-dimensional sewer flow model (SFM). Unlike conventional models limited to either rainfall-induced or sewer surcharge-induced flooding, UIDS captures bidirectional surface-underground interactions to simulate both processes simultaneously. The OFM employs an explicit time-stepping scheme and robust wet-dry front treatment, while a weir equation describes roof-to-ground flow exchange for numerical stability. Timing synchronization facilitates continuous OFM-SFM coupling. Benchmarking and case studies of Gangnam flood events demonstrate UIDS's ability to accurately simulate urban flooding, particularly subcritical flows. The open-source nature of UIDS allows user flexibility in accessing and modifying the MATLAB code. Ultimately, UIDS is expected to serve as an accessible and adaptable tool for urban flood modeling and risk assessment.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141541802","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}
Pub Date : 2024-07-02DOI: 10.1016/j.envsoft.2024.106128
Marcus Nóbrega Gomes Jr. , Marcio Hofheinz Giacomoni , Fabricio Alonso Richmond Navarro , Eduardo Mario Mendiondo
Hydrodynamic models with rain-on-the-grid capabilities are usually computationally expensive for automatic parameter estimation. In this paper, we present a global optimization-based algorithm to calibrate a fully distributed hydrologic-hydrodynamic and water quality model (HydroPol2D) using observed data (i.e., discharge, or pollutant concentration) as input. The algorithm finds near-optimal set of parameters to explain observed gauged data. This framework, although applied in a poorly-gauged urban catchment, is adapted for catchments with more detailed observations. The results of the automatic calibration indicate NSE 0.99 for the V-Tilted catchment, RMSE 830 mg L-1 for salt concentration pollutograph in a wooden-plane (i.e., 8.3% of the event mean concentration), and NSE 0.89 in a urban real-world catchment. This paper also explores the issue of equifinality (i.e., multiple parameters giving the same calibration performance) in model calibration indicating the performance variation of calibrating only with an outlet gauge or with multiple gauges within the catchment.
{"title":"Global optimization-based calibration algorithm for a 2D distributed hydrologic-hydrodynamic and water quality model","authors":"Marcus Nóbrega Gomes Jr. , Marcio Hofheinz Giacomoni , Fabricio Alonso Richmond Navarro , Eduardo Mario Mendiondo","doi":"10.1016/j.envsoft.2024.106128","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106128","url":null,"abstract":"<div><p>Hydrodynamic models with rain-on-the-grid capabilities are usually computationally expensive for automatic parameter estimation. In this paper, we present a global optimization-based algorithm to calibrate a fully distributed hydrologic-hydrodynamic and water quality model (HydroPol2D) using observed data (i.e., discharge, or pollutant concentration) as input. The algorithm finds near-optimal set of parameters to explain observed gauged data. This framework, although applied in a poorly-gauged urban catchment, is adapted for catchments with more detailed observations. The results of the automatic calibration indicate NSE <span><math><mo>=</mo></math></span> 0.99 for the V-Tilted catchment, RMSE <span><math><mo>=</mo></math></span> 830 mg L<sup>-1</sup> for salt concentration pollutograph in a wooden-plane (i.e., 8.3% of the event mean concentration), and NSE <span><math><mo>=</mo></math></span> 0.89 in a urban real-world catchment. This paper also explores the issue of equifinality (i.e., multiple parameters giving the same calibration performance) in model calibration indicating the performance variation of calibrating only with an outlet gauge or with multiple gauges within the catchment.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141607522","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}
Pub Date : 2024-06-28DOI: 10.1016/j.envsoft.2024.106130
Hu Jiang , Qiang Zou , Yunqiang Zhu , Yong Li , Bin Zhou , Wentao Zhou , Shunyu Yao , Xiaoliang Dai , Hongkun Yao , Siyu Chen
Machine learning has been widely applied to predict the spatial or temporal likelihood of debris flows by leveraging its powerful capability to fit nonlinear features and uncover underlying patterns or rules in the complex formation mechanisms of debris flows. However, traditional approaches, including some current machine learning-based prediction models, still have limitations when used for debris flow prediction. These include the lack of a specific network structure or model to consider the updating of debris flow critical conditions in relation to geographical background conditions, limiting the universality of prediction models when transferring them to different places. In this study, this article proposes a deep learning network designed to predict the spatiotemporal probability of rainfall-induced debris flows, incorporating the Similarity Mechanism of Debris Flow Critical Conditions (SM-DFCC). The model comprehensively integrates the mining of rainfall-triggering features and couples them with geographical background features to fit the nonlinear relationship with debris flow formation. The model underwent training using data on various historical debris flows triggered by different storms across Liangshan Prefecture from 2020 to 2022. The results indicated that: (i) the method is effective in predicting the spatiotemporal likelihood of debris flows under catchment units, with accuracy scores (ACC) ranging from 0.724 to 0.835; (ii) after optimization using the AVOA algorithm, the predictive performance of the model significantly improved, with an increase of 27.24% in ACC scores for SVC and 8.81% for XGBoost; and (iii) factor importance analysis revealed that rainfall triggering factors have higher cumulative contribution rates when distinguishing between the occurrence and non-occurrence of debris flows. In addition, taking a rainfall storm on 06, September 2020 as a case, this research quantitatively revealed the pattern of debris flow formation, where high-frequency disaster areas exhibit lower rainfall thresholds of debris flows, represented by absolute energy (AE). Despite these findings, the accuracy and reliability of rainfall data still remain the most challenging obstacle in basin/regional-scale debris flow prediction when applying this method. The integration of multiple sources of rainfall data, including station data, satellite rainfall, radar rainfall, etc., is necessary to accurately quantify the impact of rainfall on debris flow formation when applying this method to debris flow monitoring and early warning tasks. Overall, this method shows great potential in providing a scientific reference for the construction of debris flow monitoring and early warning systems in the future.
{"title":"Deep learning prediction of rainfall-driven debris flows considering the similar critical thresholds within comparable background conditions","authors":"Hu Jiang , Qiang Zou , Yunqiang Zhu , Yong Li , Bin Zhou , Wentao Zhou , Shunyu Yao , Xiaoliang Dai , Hongkun Yao , Siyu Chen","doi":"10.1016/j.envsoft.2024.106130","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106130","url":null,"abstract":"<div><p>Machine learning has been widely applied to predict the spatial or temporal likelihood of debris flows by leveraging its powerful capability to fit nonlinear features and uncover underlying patterns or rules in the complex formation mechanisms of debris flows. However, traditional approaches, including some current machine learning-based prediction models, still have limitations when used for debris flow prediction. These include the lack of a specific network structure or model to consider the updating of debris flow critical conditions in relation to geographical background conditions, limiting the universality of prediction models when transferring them to different places. In this study, this article proposes a deep learning network designed to predict the spatiotemporal probability of rainfall-induced debris flows, incorporating the Similarity Mechanism of Debris Flow Critical Conditions (SM-DFCC). The model comprehensively integrates the mining of rainfall-triggering features and couples them with geographical background features to fit the nonlinear relationship with debris flow formation. The model underwent training using data on various historical debris flows triggered by different storms across Liangshan Prefecture from 2020 to 2022. The results indicated that: (i) the method is effective in predicting the spatiotemporal likelihood of debris flows under catchment units, with accuracy scores (ACC) ranging from 0.724 to 0.835; (ii) after optimization using the AVOA algorithm, the predictive performance of the model significantly improved, with an increase of 27.24% in ACC scores for SVC and 8.81% for XGBoost; and (iii) factor importance analysis revealed that rainfall triggering factors have higher cumulative contribution rates when distinguishing between the occurrence and non-occurrence of debris flows. In addition, taking a rainfall storm on 06, September 2020 as a case, this research quantitatively revealed the pattern of debris flow formation, where high-frequency disaster areas exhibit lower rainfall thresholds of debris flows, represented by absolute energy (AE). Despite these findings, the accuracy and reliability of rainfall data still remain the most challenging obstacle in basin/regional-scale debris flow prediction when applying this method. The integration of multiple sources of rainfall data, including station data, satellite rainfall, radar rainfall, etc., is necessary to accurately quantify the impact of rainfall on debris flow formation when applying this method to debris flow monitoring and early warning tasks. Overall, this method shows great potential in providing a scientific reference for the construction of debris flow monitoring and early warning systems in the future.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141479833","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}
Pub Date : 2024-06-28DOI: 10.1016/j.envsoft.2024.106127
Alexander Marusov , Vsevolod Grabar , Yury Maximov , Nazar Sotiriadi , Alexander Bulkin , Alexey Zaytsev
The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting. Both models achieved high ROC AUC scores: 0.948 for one month ahead and 0.617 for twelve months ahead forecasts, becoming closer to perfect ROC-AUC by 54% and 16%, respectively, c.t. classic approaches.
{"title":"Long-term drought prediction using deep neural networks based on geospatial weather data","authors":"Alexander Marusov , Vsevolod Grabar , Yury Maximov , Nazar Sotiriadi , Alexander Bulkin , Alexey Zaytsev","doi":"10.1016/j.envsoft.2024.106127","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106127","url":null,"abstract":"<div><p>The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting. Both models achieved high ROC AUC scores: 0.948 for one month ahead and 0.617 for twelve months ahead forecasts, becoming closer to perfect ROC-AUC by 54% and 16%, respectively, c.t. classic approaches.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141594472","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}
Pub Date : 2024-06-27DOI: 10.1016/j.envsoft.2024.106125
Keivan Kaveh, Andreas Malcherek
Each submodel in a hydro-morphodynamic model has its own local calibration parameters, leading to a high degree of uncertainty in their application. This paper proposes a global parameterization framework of hydro-morphodynamic models, which involves the development and implementation of submodels that share some common calibration parameters. The proposed model reduces the total number of adjustable parameters while helping to better understand the physics of the problem. As a case study, a holistic 1D vertical numerical simulation of the Ems estuary has been established. This simulation is proficient in qualitatively reproducing observed profiles of vertical velocity, concentration, and velocity shear. Using the proposed global parameterization, the model is calibrated using only measured rheological data from the Ems estuary, with these parameters universally applied to all submodels, eliminating the need for separate calibration for other submodels. The simulation demonstrates a commendable agreement with measurements while concurrently reducing the number of calibration parameters.
{"title":"On the global parameterization of a 1DV hydromorphodynamic model of estuaries, the case of the Ems estuary","authors":"Keivan Kaveh, Andreas Malcherek","doi":"10.1016/j.envsoft.2024.106125","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106125","url":null,"abstract":"<div><p>Each submodel in a hydro-morphodynamic model has its own local calibration parameters, leading to a high degree of uncertainty in their application. This paper proposes a global parameterization framework of hydro-morphodynamic models, which involves the development and implementation of submodels that share some common calibration parameters. The proposed model reduces the total number of adjustable parameters while helping to better understand the physics of the problem. As a case study, a holistic 1D vertical numerical simulation of the Ems estuary has been established. This simulation is proficient in qualitatively reproducing observed profiles of vertical velocity, concentration, and velocity shear. Using the proposed global parameterization, the model is calibrated using only measured rheological data from the Ems estuary, with these parameters universally applied to all submodels, eliminating the need for separate calibration for other submodels. The simulation demonstrates a commendable agreement with measurements while concurrently reducing the number of calibration parameters.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224001865/pdfft?md5=cb56d341b9589e46adb7dd42e6319581&pid=1-s2.0-S1364815224001865-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141479819","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}
This study investigates the feasibility of using hybrid models namely Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU), for short-to-medium range streamflow forecasting in the Mahanadi River basin in India. The performance of these hybrid models is compared with that of standalone models. It investigates the impact of selected parameters and associated time lags on the model performance and offers valuable insights into the use of hybrid models for runoff simulation. The hybrid CNN-LSTM model proves to be robust in capturing the overall time series and the typical high peak flows in both the correlation-based and constant lag cases. Also, the upstream discharges play a significant role in improving the streamflow forecasting. Furthermore, the consideration of all input variables with a constant time lag equal to the basin lag time may yield better flood forecasts, even in cases where computational resources are limited.
{"title":"A novel insight on input variable and time lag selection in daily streamflow forecasting using deep learning models","authors":"Amina Khatun , M.N. Nisha , Siddharth Chatterjee , Venkataramana Sridhar","doi":"10.1016/j.envsoft.2024.106126","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106126","url":null,"abstract":"<div><p>This study investigates the feasibility of using hybrid models namely Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU), for short-to-medium range streamflow forecasting in the Mahanadi River basin in India. The performance of these hybrid models is compared with that of standalone models. It investigates the impact of selected parameters and associated time lags on the model performance and offers valuable insights into the use of hybrid models for runoff simulation. The hybrid CNN-LSTM model proves to be robust in capturing the overall time series and the typical high peak flows in both the correlation-based and constant lag cases. Also, the upstream discharges play a significant role in improving the streamflow forecasting. Furthermore, the consideration of all input variables with a constant time lag equal to the basin lag time may yield better flood forecasts, even in cases where computational resources are limited.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141479834","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}
Pub Date : 2024-06-21DOI: 10.1016/j.envsoft.2024.106124
P. Goodling , K. Belitz , P. Stackelberg , B. Fleming
Spatial machine learning models can be developed from observations with substantial unexplainable variability, sometimes called ‘noise’. Traditional point-scale metrics (e.g., R2) alone can be misleading when evaluating these models. We present a multi-scale performance evaluation (MPE) using two additional scales (distributional and geostatistical). We apply the MPE framework to predictions of depth to bedrock (DTB) in the Delaware River Basin. Geostatistical analysis shows that approximately one third of the DTB variance is at spatial scale smaller than 2 km. Hence, we interpret our point-scale R2 of 0.3 (testing data) to be sufficient for regional-scale modelling. Bias-correction methods improve performance at two of the three MPE scales: point-scale change is negligible, while distributional and geostatistical performance improves. In contrast, bias correction applied to a global DTB model does not improve MPE performance. This work encourages scale-appropriate performance evaluations to enable effective model intercomparison.
{"title":"A spatial machine learning model developed from noisy data requires multiscale performance evaluation: Predicting depth to bedrock in the Delaware river basin, USA","authors":"P. Goodling , K. Belitz , P. Stackelberg , B. Fleming","doi":"10.1016/j.envsoft.2024.106124","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106124","url":null,"abstract":"<div><p>Spatial machine learning models can be developed from observations with substantial unexplainable variability, sometimes called ‘noise’. Traditional point-scale metrics (e.g., R<sup>2</sup>) alone can be misleading when evaluating these models. We present a multi-scale performance evaluation (MPE) using two additional scales (distributional and geostatistical). We apply the MPE framework to predictions of depth to bedrock (DTB) in the Delaware River Basin. Geostatistical analysis shows that approximately one third of the DTB variance is at spatial scale smaller than 2 km. Hence, we interpret our point-scale R<sup>2</sup> of 0.3 (testing data) to be sufficient for regional-scale modelling. Bias-correction methods improve performance at two of the three MPE scales: point-scale change is negligible, while distributional and geostatistical performance improves. In contrast, bias correction applied to a global DTB model does not improve MPE performance. This work encourages scale-appropriate performance evaluations to enable effective model intercomparison.</p></div>","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1364815224001853/pdfft?md5=7fedebb9a98cc4eebaa6f029bad61dfe&pid=1-s2.0-S1364815224001853-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141444188","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}
Pub Date : 2024-06-20DOI: 10.1016/j.envsoft.2024.106113
Robertas Damaševičius
{"title":"Commentary on “Cloud-based urgent computing for forest fire spread prediction” by Fraga et al.","authors":"Robertas Damaševičius","doi":"10.1016/j.envsoft.2024.106113","DOIUrl":"https://doi.org/10.1016/j.envsoft.2024.106113","url":null,"abstract":"","PeriodicalId":310,"journal":{"name":"Environmental Modelling & Software","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141439145","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}