Environmental Modelling & Software最新文献

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.

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.

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.

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.

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.

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.

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.

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.

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.