District-Level Rainfall and Cloudburst Prediction Using XGBoost: A Machine Learning Approach for Early Warning Systems

Guru Dayal Kumar, Shekhar Tyagi, Kalandi Charan Pradhan, Akshat Shah

Abstract


This research presents a novel methodology for cloudburst forecasting using the XGBoost (Extreme Gradient Boosting) machine learning algorithm. With the escalating impact of climate change, accurately predicting extreme weather events like cloudbursts is crucial due to their potential to trigger floods. Cloudburst events were identified from daily rainfall data. Our study leverages historical weather data, focusing on intricate rainfall patterns, to forecast future cloudburst occurrences. Comparative analysis against Random Forest and LSTM models confirmed XGBoost’s effectiveness, consistently outperforming alternatives across multiple performance metrics. The XGBoost model, known for its ability to handle complex datasets, demonstrated strong predictive performance, with an RMSE of 0.12 and an MAE of 0.09, indicating high accuracy. This research provides a reliable tool for advanced weather forecasting and early warning systems, offering valuable support to policymakers, disaster management teams, and agricultural planners in mitigating risks associated with extreme rainfall events.

Full Text:

PDF

References


Ams: American metrological society. https:

//glossary.ametsoc.org/wiki/Welcome/. Ac-

cessed: March 23, 2024.

Em-dat: The international disaster database.

https://www.emdat.be/. Accessed: March 23,

Flood Management Information System, Bi-

har. https://www.fmiscwrdbihar.gov.in/

fmis/history.html. Accessed on February 12,

Know your risk. http://bsdma.org/

Know-Your-Risk.aspx?id=3. Accessed: March

, 2024.

NDRF Flood Operations 2019. https://ndrf.

gov.in/operations/flood-2019. Accessed on

February 12, 2024.

Water resources information system for in-

dia. https://indiawris.gov.in/wris/#/

DataDownload. Accessed: March 23, 2024.

Vidhi Bharti and Charu Singh. Evaluation of er-

ror in trmm 3b42v7 precipitation estimates over

the himalayan region. Journal of Geophysical Re-

search: Atmospheres, 120(24):12458–12473, 2015.

WE Bonnett. Cloudburst near citrus, cal.

Monthly Weather Review, 32(8):358–358, 1904.

Tianqi Chen and Carlos Guestrin. Xgboost: A

scalable tree boosting system. In Proceedings of

the 22nd acm sigkdd international conference on

knowledge discovery and data mining, pages 785–

, 2016.

A Chevuturi, AP Dimri, Someshwar Das, A Ku-

mar, and D Niyogi. Numerical simulation of an in-

tense precipitation event over rudraprayag in the

central himalayas during 13–14 september 2012.

Journal of Earth System Science, 124:1545–1561,

Colin Clark. The cloudburst of 2 july 1893 over

the cheviot hills, england. Weather, 60(4):92–97,

Sining Cuevas. Examining climate change adap-

tation measures: an early warning system in

the philippines. International Journal of Climate

Change Strategies and Management, 4(4):358–

, 2012.

Someshwar Das, Raghavendra Ashrit, and

MW Moncrieff. Simulation of a himalayan cloud-

burst event. Journal of earth system science,

:299–313, 2006.

John A Day and Vincent J Schaefer. Peterson

First Guide to Clouds and Weather. Houghton

Mifflin, 1991.

AP Dimri and SK Dash. Wintertime climatic

trends in the western himalayas. Climatic change,

(3-4):775–800, 2012.

Jianhua Dong, Wenzhi Zeng, Lifeng Wu, Jiesheng

Huang, Thomas Gaiser, and Amit Kumar Srivas-

tava. Enhancing short-term forecasting of daily

precipitation using numerical weather prediction

bias correcting with xgboost in different regions

of china. Engineering Applications of Artificial

Intelligence, 117:105579, 2023.

JS Douglas. A california cloudburst. Monthly

Weather Review, 36(9):299–300, 1908.

Storm Dunlop. The weather identification hand-

book. Globe Pequot, 2003.

Storm Dunlop. A dictionary of weather. OUP

Oxford, 2008.

AD Elmer. Cloudbursts. Monthly Weather Re-

view, 30(10):478–478, 1902.

Bapon SHM Fakhruddin and Lauren Schick. Ben-

efits of economic assessment of cyclone early

warning systems-a case study on cyclone evan in

samoa. Progress in Disaster Science, 2:100034,

Center for Climate Change and Sustain-

ability Studies. Bengaluru Floods: Case of

Urban Flooding. https://climatetrends. in/wp-content/uploads/2023/04/

bengaluru-floods-case-of-urban-flooding.

pdf. Accessed on February 12, 2024.

Juliane Loraine Fry, Hans-F Graf, Richard Grot-

jahn, Marilyn Raphael, Clive Saunders, and

Richard Whitaker. The encyclopedia of weather

and climate change: a complete visual guide. Uni-

versity of California Press Berkeley, CA, 2010.

Kumar Gaurav, Fran¸cois M´etivier, Olivier De-

vauchelle, Rajiv Sinha, Hugo Chauvet, Morgane

Houssais, and H´el`ene Bouquerel. Morphology of

the kosi megafan channels. Earth Surface Dynam-

ics, 3(3):321–331, 2015.

Mahmoud Yousef M Ghoneem and Ahmed

Khaled A Elewa. The early warning application

role in facing the environmental crisis and disas-

ters:’preliminarily risk management strategy for

the greater city of cairo’. Spatium, pages 40–48,

Bhupendra Nath Goswami, Vengatesan Venu-

gopal, Debasis Sengupta, MS Madhusoodanan,

and Prince K Xavier. Increasing trend of extreme

rain events over india in a warming environment.

Science, 314(5804):1442–1445, 2006.

P Goswami and KV Ramesh. Extreme rainfall

events: vulnerability analysis for disaster man-agement and observation system design. Current

Science, pages 1037–1044, 2008.

P Guhathakurta, OP Sreejith, and PA Menon.

Impact of climate change on extreme rainfall

events and flood risk in india. Journal of earth

system science, 120:359–373, 2011.

Umesh K Haritashya, Pratap Singh, Naresh Ku-

mar, and Yatveer Singh. Hydrological importance

of an unusual hazard in a mountainous basin:

flood and landslide. Hydrological Processes: An

International Journal, 20(14):3147–3154, 2006.

Robert E Horton and George T Todd. Cloudburst

rainfall at taborton, ny, august 10, 1920. Monthly

Weather Review, 49(4):202–204, 1921.

India Meteorological Department. Press release

no. 2555/2023, October 1 2023. Last accessed:

August 13, 2024.

India Meteorological Department. Monsoon fre-

quently asked questions, n.d. Accessed: March

, 2024.

India Meteorological Department (IMD). Under-

standing cloudbursts and their impacts, 2020. Ac-

cessed on [Insert Access Date if online].

D Izzo. Fisica delle nubi e delle precipitazioni.

Manuale di Meteorologia. Giuliacci M, Giuliacci

A, Corazzon P (eds). Alpha Test: Milano, pages

–524, 2010.

Warren R King. Record cloudburst flood in carter

county, tenn., june 13, 1924. Monthly Weather

Review, 52(6):311–313, 1924.

Charles D Kolstad and Frances C Moore. Esti-

mating the economic impacts of climate change

using weather observations. Review of Environ-

mental Economics and Policy, 2020.

V Krishnamurthy. Extreme events and trends in

the Indian summer monsoon. Center of Ocean-

Land-Atmosphere Studies, 2011.

Ameya Kshirsagar and Parth Sanghavi.

Geothermal, oil and gas well subsurface

temperature prediction employing machine

learning. In 47 th workshop on geothermal

reservoir engineering. https://pangea. stanford.

edu/ERE/db/GeoConf/papers/SGW/2022/Kshirsagar.

pdf, 2022.

Guru Dayal Kumar and Kalandi Charan Prad-

han. Assessing the district-level flood vulnerabil-

ity in bihar, eastern india: An integrated socioe-

conomic and environmental approach. Environ-

mental Monitoring and Assessment, 196(9):799,

Guru Dayal Kumar, Kalandi Charan Pradhan,

and Shekhar Tyagi. Deep learning forecasting:

An lstm neural architecture based approach to

rainfall and flood impact predictions in bihar.

Procedia Computer Science, 235:1455–1466, 2024.

Guru Dayal Kumar, Shekhar Tyagi, and Ka-

landi Charan Pradhan. Predictive ml analysis:

Rainfall & flood vulnerability in bihar, india. In

Artificial Intelligence and Information Technolo-

gies, pages 447–453. CRC Press, 2024.

Manosi Lahiri. Bihar geographic information sys-

tem. Popular Prakashan, Bombay, IN, 1992.

John Lovel. Thunderstorm, cloudburst and flood

at langtoft, east yorkshire, july 3rd, 1892. Quar-

terly Journal of the Royal Meteorological Society,

(85):1–15, 1893.

Darren Lumbroso, Emma Brown, and Nicola

Ranger. Stakeholders’ perceptions of the over-

all effectiveness of early warning systems and risk

assessments for weather-related hazards in africa,

the caribbean and south asia. Natural Hazards,

:2121–2144, 2016.

Xiongfa Mai, Haiyan Zhong, and Ling Li. Re-

search on rain or shine weather forecast in precip-

itation nowcasting based on xgboost. In The In-

ternational Conference on Natural Computation,

Fuzzy Systems and Knowledge Discovery, pages

–1319. Springer, 2020.

Val´erie Masson-Delmotte, Panmao Zhai, Anna

Pirani, Sarah L Connors, Clotilde P´ean, So-

phie Berger, Nada Caud, Y Chen, L Goldfarb,

MI Gomis, et al. Climate change 2021: the physi-

cal science basis. Contribution of working group I

to the sixth assessment report of the intergovern-

mental panel on climate change, 2(1):2391, 2021.

A Austin Miller. Cause and effect in a welsh

cloudburst. Weather, 6(6):172–179, 1951.

S Nandargi and ON Dhar. Extreme rainstorm

events over the northwest himalayas during 1875–

Journal of Hydrometeorology, 13(4):1383–

, 2012.

Giuseppe Orlando and Michele Bufalo. A general-

ized two-factor square-root framework for model-

ing occurrences of natural catastrophes. Journal

of Forecasting, 41(8):1608–1622, 2022.

Isidoro Orlanski. A rational subdivision of scales

for atmospheric processes. Bulletin of the Amer-

ican Meteorological Society, pages 527–530, 1975.

Ahmedbahaaaldin Ibrahem Ahmed Osman,

Ali Najah Ahmed, Ming Fai Chow, Yuk FengHuang, and Ahmed El-Shafie. Extreme gradient

boosting (xgboost) model to predict the ground-

water levels in selangor malaysia. Ain Shams

Engineering Journal, 12(2):1545–1556, 2021.

AC Pandey, Suraj Kumar Singh, and

MS Nathawat. Waterlogging and flood haz-

ards vulnerability and risk assessment in indo

gangetic plain. Natural hazards, 55:273–289,

Bikash Ranjan Parida, Sailesh N Behera, Oinam

Bakimchandra, Arvind Chandra Pandey, and

Nilendu Singh. Evaluation of satellite-derived

rainfall estimates for an extreme rainfall event

over uttarakhand, western himalayas. Hydrology,

(2):22, 2017.

Santhanam Ramraj, Nishant Uzir, R Sunil, and

Shatadeep Banerjee. Experimenting xgboost al-

gorithm for prediction and classification of dif-

ferent datasets. International Journal of Control

Theory and Applications, 9(40):651–662, 2016.

Jun Rentschler, Melda Salhab, and Bramka Arga

Jafino. Flood exposure and poverty in 188 coun-

tries. Nature communications, 13(1):3527, 2022.

Chandan Roy, Saroje Kumar Sarkar, Johan

˚Aberg, and Rita Kovordanyi. The current cyclone

early warning system in bangladesh: providers’

and receivers’ views. International journal of dis-

aster risk reduction, 12:285–299, 2015.

Md Shahjahan. Assessing the cyclone early warn-

ing services of women, children and person with

disability: a case study in Nijhumdwip. PhD the-

sis, BRAC Univeristy, 2018.

Anand Shankar, Ashish Kumar, Bikash Chan-

dra Sahana, and Vivek Sinha. A case study of

heavy rainfall events and resultant flooding dur-

ing the summer monsoon season 2020 over the

river catchments of north bihar, india. Vayuman-

dal, 48(2):17–28, 2022.

Susan Solomon. Climate change 2007-the physical

science basis: Working group I contribution to the

fourth assessment report of the IPCC, volume 4.

Cambridge university press, 2007.

Nicholas Herbert Stern. The economics of climate

change: the Stern review. cambridge University

press, 2007.

Robert Szczepanek. Daily streamflow forecasting

in mountainous catchment using xgboost, light-

gbm and catboost. Hydrology, 9(12):226, 2022.

Ashok Kumar Tripathi, PK Gupta, Hemraj Saini,

and Geetanjali Rathee. Mvi and forecast preci-

sion upgrade of time series precipitation infor-

mation for ubiquitous computing. Informatica,

(5), 2023.

Gaurav Tripathi, Arvind Chandra Pandey, and

Bikash Ranjan Parida. Flood hazard and risk

zonation in north bihar using satellite-derived his-

torical flood events and socio-economic data. Sus-

tainability, 14(3):1472, 2022.

BM Varney. The great hailstorm in south-

eastern new hampshire and northeastern mas-

sachusetts, july 17, 1924. Monthly Weather Re-

view, 52(8):394–395, 1924.

Ralph R Woolley. Cloudburst floods in utah: Us

geol. Survey, Water, 1946.

World Meteorological Organization. State of cli-

mate services 2020 report: Move from early warn-

ings to early action, 2020.

Mohammad Zakwan and Zeenat Ara. Statistical

analysis of rainfall in bihar. Sustainable Water

Resources Management, 5(4):1781–1789, 2019.




DOI: https://doi.org/10.31449/inf.v49i2.7612

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.