Analysis of six years of micrometeorological records and data revealed strong interactions between relative humidity and evapotranspiration. Daily evapotranspiration estimates for cloudy regions need more information that relies solely on meteorological data, a primary focus of this study.
This study proposes a new deep recurrent neural network approach, Neural Runoff Model (NRM), which has been applied on 125 USGS streamflow gages in the State of Iowa for predicting the next 120 h due to the difficult nature of accurate streamflow forecasting. The proposed model outperforms the streamflow persistence, ridge regression and random forest regression on majority of the gages. The model has also shown strong predictive power and can be used for long-term streamflow predictions.
In this study, a web-based decision support tool (DST) was developed for hydrological multi-hazard analysis while employing gamification techniques to introduce a competitive element. The serious gaming environment provides functionalities for intuitive management, visualization, and analysis of geospatial, hydrological, and economic data to help stakeholders in the decision-making process regarding hydrological hazard preparedness and response. The framework is an engaging, accessible, and collaborative serious game environment facilitating the relationship between the environment and communities.
Web-based distributed volunteer computing enables scientists to constitute platforms that can be used for computational tasks by using potentially millions of computers connected to the internet. The framework provides distribution and scaling capabilities for projects with user bases of thousands of volunteers. As a case study, we tested and evaluated the proposed framework with a large-scale hydrological flood forecasting model.
Researchers have been developing physical and machine learning models for decades to predict runoff using rainfall data sets, and this study presents an application of a prediction model based on LSTM and the seq2seq structure to estimate hourly rainfall‐runoff.
LSTM = Long Short-Term Memory
seq2seq = sequence to sequence modeling
Citizen science opportunities for environmental monitoring have increased with the advances in smart phone capabilities and their growing availability. This project describes a new method to accurately measure river levels using smartphone sensors. Pictures of the same point on the river’s surface are taken to perform calculations based on the GPS location and spatial orientation of the smartphone. The proposed implementation is significantly more accessible than existing water measuring systems while offering similar accuracy.
The paper focuses on a participation-based serious gaming application developed to enhance multi-jurisdictional collaborative planning and decision making for mitigation of multiple hazards related to water, such as flooding, soil erosion, and water quality. The game is integrated into the Iowa Watershed Decision Support System (IoWaDSS).