We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Papers
61,005 resultsShowing papers similar to Predicting tidal level in tropical Eastern Bintan waters using residual long short-term memory
ClearModeling of daily groundwater level using deep learning neural networks
Researchers applied a CNN-biLSTM deep learning model to predict daily groundwater levels, finding it outperformed conventional modeling approaches by capturing both spatial patterns and temporal dependencies in the data. The method offers improved accuracy for groundwater monitoring, which is critical for managing increasingly stressed freshwater resources.
A significant wave height prediction method based on deep learning combining the correlation between wind and wind waves
Researchers developed a significant wave height prediction model based on the ConvLSTM deep learning algorithm that incorporates correlations between wind fields and wave generation. A Mask and Replace optimization mechanism improved long-term prediction accuracy, and the model showed high spatial and temporal resolution performance in regional ocean forecasting.
Ocean Current Prediction Using the Weighted Pure Attention Mechanism
Researchers developed a deep learning model using a weighted pure attention mechanism for ocean current prediction, finding that adding a weight parameter to optimize attention toward key elements significantly improved prediction accuracy across wide time ranges and spatial scales. The approach outperformed standard attention-mechanism models and represents the first application of weighted pure attention to ocean current forecasting.
Machine Learning for Flood Resiliency—Current Status and Unexplored Directions
This review examines the current state of machine learning (ML) applications across the full flood management spectrum, finding that deep learning models like long short-term memory networks perform well for reservoir flow prediction, while reinforcement learning shows promise for managing low-impact development systems in pluvial flood control.
The Utilization of Satellite Data and Machine Learning for Predicting the Inundation Height in the Majalaya Watershed
This paper is not about microplastics; it uses satellite rainfall data, HEC-RAS flood modeling, and artificial neural networks to predict flood inundation heights in the Majalaya Watershed of Indonesia.
Machine Learning for Flood Resiliency—Current Status and Unexplored Directions
This systems review assessed machine learning applications across the flood management spectrum—reservoir inflow prediction (LSTM), levee failure detection (CNN), and low-impact development control (reinforcement learning). The paper is focused on flood resilience engineering and does not contain microplastics research.
Detection of Plastic Waste in Ocean Using Machine Learning Based Bi- LSTM With Triplet Attention Mechanism
Researchers developed a machine learning model using a bidirectional LSTM architecture with triplet attention mechanism to detect plastic waste in ocean environments, addressing the challenge of tracking plastic flow from rivers into marine ecosystems.
A novel filtering method for geodetically determined ocean surface currents using deep learning
Researchers used deep learning to improve the accuracy of ocean current maps derived from satellite measurements of sea level and gravity. Better ocean current mapping helps scientists track where microplastics travel and accumulate in the ocean once they enter from rivers and coastlines.
A Hybrid Deep Learning Model for Wind and Solar Power Forecasting in Smart Grids
Researchers developed a hybrid deep learning model combining multiple neural network architectures to improve wind and solar power forecasting in smart grids, addressing limitations of traditional models in handling the complex, non-linear, and time-varying nature of renewable energy output.
Distribution and Structure of China–ASEAN’s Intertidal Ecosystems: Insights from High-Precision, Satellite-Based Mapping
Researchers used multi-source satellite data to create high-precision maps of intertidal ecosystems across the China-ASEAN region, distinguishing between mangroves, salt marshes, and tidal flats. They developed an improved classification framework to address inconsistencies in previous mapping efforts. The study provides a valuable baseline for monitoring how climate change and human activities are affecting these ecologically important coastal zones.
Spatiotemporal Forecasting and Environmental Driver Modeling of Marine Microplastic Pollution: an Interpretable Deep Learning Approach for Sustainable Ocean Policy
Researchers developed an interpretable deep learning model integrating historical microplastic sampling data, seasonal patterns, and large-scale ocean-atmosphere climate indices to forecast spatiotemporal marine microplastic distribution, identifying climate drivers and offering a policy-relevant tool for ocean pollution management.
Machine learning approach for automated beach waste prediction and management system: A case study of Mumbai
Researchers developed a machine learning system to predict beach waste generation patterns in Mumbai, aiming to enable more effective and automated waste management for one of the world's most polluted coastal cities.
Water Level Prediction through Hybrid SARIMA and ANN Models Based on Time Series Analysis: Red Hills Reservoir Case Study
Researchers developed hybrid SARIMA and artificial neural network models to predict reservoir water levels at Red Hills Reservoir in India, aiming to improve water resource management under changing climatic conditions.
Advancements and Challenges in Deep Learning-Driven Marine Data Assimilation: A Comprehensive Review
This review surveys how deep learning is being applied to marine data assimilation — the process of combining model predictions with real-world observations to improve ocean forecasting. The authors identify key challenges in data quality, model interpretability, and integration with physical ocean models.
PM2.5 Concentration Prediction Based on CNN-BiLSTM and Attention Mechanism
Researchers developed a CNN-BiLSTM deep learning model combined with an attention mechanism to predict PM2.5 concentrations, finding that the hybrid model outperformed individual architectures and achieved high accuracy in forecasting air quality.
Enhanced spatiotemporal mapping of urban wetland microplastics: An interpretable CNN-GRU approach using satellite imagery and limited samples
Researchers built an interpretable CNN-GRU deep learning model combining satellite remote sensing with limited in-situ measurements to map microplastic distribution in urban wetlands with enhanced spatiotemporal resolution, enabling more comprehensive monitoring with less field sampling.
Mapping the plastic legacy: Geospatial predictions of a microplastic inventory in a complex estuarine system using machine learning
Researchers applied machine learning techniques to develop geospatial predictions of microplastic inventory in a complex estuarine system, overcoming the limitations of coarse ocean basin models by accounting for the intricate geomorphological and hydrodynamic conditions that govern sediment-associated microplastic distribution.
Model Arus Permukaan Teluk Lampung pada Musim Peralihan II dengan Pendekatan Hidrodinamika
This study modeled surface current patterns in Lampung Bay, Indonesia, during the second transition season using hydrodynamic modeling. Understanding coastal current patterns is relevant to predicting how microplastics and other pollutants disperse in Indonesian coastal waters.
Predicting microplastic accumulation zones and shoreline changes along the Kelantan coast, Malaysia, using integrated GIS and ANN models
Researchers combined GIS with an artificial neural network to predict microplastic accumulation zones along Malaysia's Kelantan coast, achieving R=0.972 predictive accuracy and identifying shoreline erosion-prone areas as the primary deposition hotspots for microplastic pollution.
SDUST2023BCO: a global seafloor model determined from a multi-layer perceptron neural network using multi-source differential marine geodetic data
This study used a neural network to build a new global seafloor topography model by combining multiple sources of marine depth data, including satellite altimetry and ship soundings. The resulting model provides more accurate ocean floor maps, which are important for understanding marine environments, ocean circulation, and seafloor geology.
Classification of Eddy Sea Surface Temperature Signatures Under Cloud Coverage
Researchers developed a deep learning approach to classify mesoscale oceanic eddy signatures in sea surface temperature satellite images, overcoming the challenges posed by complex eddy structures and cloud coverage that corrupts large fractions of imagery.
An Effective Machine Learning Scheme to Analyze and Predict the Concentration of Persistent Pollutants in the Great Lakes
Scientists applied multiple machine learning methods to predict concentrations of persistent organic pollutants in the Great Lakes, finding that LSTM neural networks outperformed simpler models for these complex time-series patterns. Similar predictive modeling could track microplastic concentrations in large water bodies over time.
Tidal intensity and suspended sediment concentration drive microplastic distribution in the Pearl River Estuary: Insights from remote sensing retrieval
Field measurements showed that tidal intensity and suspended sediment concentrations are key drivers of microplastic transport in coastal and estuarine waters. The results help explain why microplastic concentrations fluctuate with tidal cycles and inform models predicting where plastics accumulate in dynamic coastal zones.
Analysing of rainfall-runoff modelling using a hybrid DNN-SGD optimisation in Sub Basin of Brahmaputra River, India
Researchers developed a hybrid deep neural network optimized with stochastic gradient descent (DNN-SGD) for rainfall-runoff modelling in a sub-basin of the Brahmaputra River in India, evaluating model accuracy using coefficient of determination, mean squared error, and root mean squared error metrics. The study demonstrated that the DNN-SGD model achieved superior runoff prediction performance compared to conventional hydrological approaches in the monsoon-dominated river basin.