Ushaa Eswaran
C. Pushpalatha
Shaik Beebi
- Principal and Professor, Department of ECE, Indira Institute of Technology and Sciences, Markapur, Andhra Pradesh, India
- Assistant Professor, Department of ECE, Indira Institute of Technology and Sciences, Markapur, Andhra Pradesh, India
- Assistant Professor, Department of ECE, Indira Institute of Technology and Sciences, Markapur, Andhra Pradesh, India
Abstract
This paper presents the development and real-world deployment of an intelligent system for flood monitoring and automated dam gate control using artificial intelligence (AI) and internet of things (IoT) sensors. Supervised machine learning models are developed to predict floods up to 48 hours in advance. An automated dam gate operation system is designed to leverage the flood forecasts and real-time stream water levels for emergency control. The complete end-to-end infrastructure is installed across a flood-prone river basin spanning 50 sq. km, with sensors streaming data to an integrated software platform.
The recurrent neural network model performs accurate hourly flood predictions across multiple lead times with an average precision of 0.82 and recall of 0.79 on the testing dataset. The automated dam gate system initiates opening/closing actions based on the flood predictions, while maintaining water levels within the safe operation zone 95.6% of the deployment duration. The end-to-end system provides emergency responders 36 hours of early warning on average and reduces risk of infrastructure failures and downstream inundation.
Keywords: flood monitoring, dam gate control, machine learning, internet of things, sensors
[This article belongs to International Journal of Data Structure Studies(ijdss)]
var fieldValue = “[user_role]”;
if (fieldValue == ‘indexingbodies’) {
document.write(‘Full Text PDF‘);
}
else if (fieldValue == ‘administrator’) { document.write(‘Full Text PDF‘); }
else if (fieldValue == ‘ijdss’) { document.write(‘Full Text PDF‘); }
else { document.write(‘ ‘); }
References
Castelletti, A., Galelli, S., Restelli, M., & Soncini-Sessa, R. (2010). Tree-based reinforcement learning for optimal water reservoir operation. Water Resources Research, 46(9). https://doi.org/10.1029/2009WR008898
Du, J., Qian, L., Rui, H., Zuo, T., Zheng, D., Xu, Y., & Xu, C. Y. (2012). Assessing the effects of urbanization on annual runoff and flood events using an integrated hydrological modeling system for Qinhuai River basin, China. Journal of Hydrology, 464-465, 127-139. https://doi.org/10.1016/j.jhydrol.2012.06.057
Fan, F. M., Deng, K., Zhou, S. L., Li, X., Wang, G. Q., & Chan, P. W. (2019). Forecasting flash floods in mountainous areas using machine learning methods – Case study for Longnan City, China. Journal of Hydrology, 568, 823-840. https://doi.org/10.1016/j.jhydrol.2018.11.058
France-Presse, A. (2017, February 13). California ‘bullet train’ hits a big sinking feeling. The Telegraph India. https://www.telegraphindia.com/world/california-bullet-train-hits-a-big-sinking-feeling/cid/1201009
Gers, F. A., Schmidhuber, J., & Cummins, F. (1999). Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10), 2451–2471. https://doi.org/10.1162/089976699300016112
Hornsby, D., & Jeswiet, J. (2019). Application of artificial intelligence methods to forecasting dam inflows for real-time optimization. Canadian Water Resources Journal / Revue Canadienne Des Ressources Hydriques, 45(1), 28–44. https://doi.org/10.1080/07011784.2019.1652381
Islam, S., Rico-Ramirez, M. A., Han, D., & Srivastava, P. K. (2015). Artificial intelligence techniques for clouds and rain precipitation nowcasting: A review. Artificial Intelligence Review, 45(3), 345–392. https://doi.org/10.1007/s10462-015-9452-5
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., & Herrnegger, M. (2018). Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrology and Earth System Sciences, 22(11), 6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Maier, H. R., Jain, A., Dandy, G. C., & Sudheer, K. P. (2010). Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions. Environmental Modelling & Software, 25(8), 891-909. https://doi.org/10.1016/j.envsoft.2010.02.003
Olivera, F., & Raina, R. (2003). Flood early warning systems. Encyclopedia of Water Science, 469-473.
Ushaa Eswaran, et al. (2011). Disease detection using nanosensor models. International Journal of Advances in Science and Technology, 106-120.
Ushaa Eswaran, et al. (2012). Modeling and simulation of nanosensor arrays for automated disease detection and drug delivery unit. International Journal of Advances in Engineering & Technology, 2(1), 564-577.
Ushaa Eswaran, et al. (2009). Disease detection using pattern recognition techniques. GITAM Journal of Information Communication Technology, 1(2), 34-37.
Ushaa Eswaran, et al. (2012). Embedded system based automated drug delivery unit and microfluidics for drug discovery. International Journal of Advanced Research in Computer and Communication Engineering, 13-20. https://doi.org/10.17148/IJARCCE
Ushaa Eswaran, et al. (2018). Design and analysis of high sensitive microcantilever based biosensor for CA 15-3 biomarker detection. Journal of Applied Science and Computations, 5(7), 682-698. https://doi.org/10.26811/1076-5153.2018.5.7.10264
World Meteorological Organization (WMO). (2022). State of climate services 2022: Water. https://reliefweb.int/report/world/state-of-climate-services-2022-water-enarfrzh
| Volume | 01 |
| Issue | 02 |
| Received | December 5, 2023 |
| Accepted | December 12, 2023 |
| Published | December 22, 2023 |
function myFunction2() {
var x = document.getElementById(“browsefigure”);
if (x.style.display === “block”) {
x.style.display = “none”;
}
else { x.style.display = “Block”; }
}
document.querySelector(“.prevBtn”).addEventListener(“click”, () => {
changeSlides(-1);
});
document.querySelector(“.nextBtn”).addEventListener(“click”, () => {
changeSlides(1);
});
var slideIndex = 1;
showSlides(slideIndex);
function changeSlides(n) {
showSlides((slideIndex += n));
}
function currentSlide(n) {
showSlides((slideIndex = n));
}
function showSlides(n) {
var i;
var slides = document.getElementsByClassName(“Slide”);
var dots = document.getElementsByClassName(“Navdot”);
if (n > slides.length) { slideIndex = 1; }
if (n (item.style.display = “none”));
Array.from(dots).forEach(
item => (item.className = item.className.replace(” selected”, “”))
);
slides[slideIndex – 1].style.display = “block”;
dots[slideIndex – 1].className += ” selected”;
}