Abstract
With significant development of sensors and Internet of things, researchers nowadays can easily know what happens in physical space by acquiring time-varying values of various factors. Essentially, growing data category and size greatly contribute to solve problems happened in physical space. In this paper, we aim to solve a complex problem that affects both cities and villages, i.e., flood. To reduce impacts induced by floods, hydrological factors acquired from physical space and data-driven models in cyber space have been adopted to accurately forecast floods. Considering the significance of modeling attention capability among hydrology factors, we believe extraction of discriminative hydrology factors not only reflect natural rules in physical space, but also optimally model iterations of factors to forecast run-off values in cyber space. Therefore, we propose a novel data-driven model named as STA-LSTM by integrating Long Short-Term Memory (LSTM) structure and spatiotemporal attention module, which is capable of forecasting floods for small- and medium-sized rivers. The proposed spatiotemporal attention module firstly explores spatial relationship between input hydrological factors from different locations and run-off outputs, which assigns time-varying weights to various factors. Afterwards, the proposed attention module allocates temporal-dependent weights to hidden output of each LSTM cell, which describes significance of state output for final forecasting results. Taking Lech and Changhua river basins as cases of physical space, several groups of comparative experiments show that STA-LSTM is capable to optimize complexity of mathematically modeling floods in cyber space.
Highlights
As more sensors are applied to acquire variant data from physical space, researchers try to build a corresponding cyber space to describe inherent mathematical relationship between sensor acquired factors and results, which provides users a great deal of convenience to find novel solutions for problems in the real world
Hard attention can be comprehended as spatial selection for salient regions, which leads the input areas to be processed as different parts with values of 0 or 1
We firstly offer a brief introduction to mathematical theory of Long Short-Term Memory (LSTM) cell. en, we explain how attention scheme improves accuracy of flood forecasting
Summary
As more sensors are applied to acquire variant data from physical space, researchers try to build a corresponding cyber space to describe inherent mathematical relationship between sensor acquired factors and results, which provides users a great deal of convenience to find novel solutions for problems in the real world. Based on core ideas to forecast, we divide their proposed methods into two categories: physical model [3, 4] and data-driven model [5, 6]. Following idea of hard attention, He et al [30] propose a convolutional neural network, named as Text-CNN, to involve attention scheme for scene text detection Their scheme extracts salient regions as informative parts of input images, and selects informative features from feature pools for more accurate detection. We get hydrological data about Changhua river basin from cooperation China government Our goal for both river basins is to realize forecasting of surface run-off at their converge locations (represented as red circles at Figure 1) through the proposed STA-LSTM model. The proposed model adopts multiple hydrological factors as inputs, including precipitation, evaporation, soil tension water, temperature, and wind
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
