当前位置: X-MOL 学术J. Water Clim. Chang. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Flood prediction based on weather parameters using deep learning
Journal of Water & Climate Change ( IF 2.7 ) Pub Date : 2020-12-01 , DOI: 10.2166/wcc.2019.321
Suresh Sankaranarayanan 1 , Malavika Prabhakar 2 , Sreesta Satish 3 , Prerna Jain 4 , Anjali Ramprasad 5 , Aiswarya Krishnan 6
Affiliation  

Today, India is one of the worst flood-affected countries in the world, with the recent disaster in Kerala in August 2018 being a prime example. A good amount of work has been carried out by employing Internet of Things (IoT) and machine learning (ML) techniques in the past for flood occurrence based on rainfall, humidity, temperature, water flow, water level etc. However, the challenge is that no one has attempted the possibility of occurrence of flood based on temperature and rainfall intensity. So accordingly Deep Neural Network has been employed for predicting the occurrence of flood based on temperature and rainfall intensity. In addition, a deep learning model is compared with other machine learning models (support vector machine (SVM), K-nearest neighbor (KNN) and Naïve Bayes) in terms of accuracy and error. The results indicate that the deep neural network can be efficiently used for flood forecasting with highest accuracy based on monsoon parameters only before flood occurrence.



中文翻译:

使用深度学习基于天气参数进行洪水预报

如今,印度是世界上受洪灾最严重的国家之一,最近的一次灾难就是2018年8月在喀拉拉邦发生的灾难。过去,通过基于降雨,湿度,温度,水流量,水位等的洪水泛滥,采用物联网(IoT)和机器学习(ML)技术已经进行了大量工作。然而,挑战在于没有人尝试根据温度和降雨强度发生洪水的可能性。因此,相应地,深度神经网络已被用于基于温度和降雨强度来预测洪水的发生。此外,在准确性和误差方面,将深度学习模型与其他机器学习模型(支持向量机(SVM),K近邻(KNN)和朴素贝叶斯)进行了比较。

更新日期:2020-12-15
down
wechat
bug