Abstract
This study evaluates the reliability of merged satellite precipitation products based on single machine learning (SML) and double machine learning (DML) algorithms to estimate meteorological drought events over Kenya from 2000 to 2019. This study selected four SML algorithms, including Random Forest (RF), Support Vector Machine (SVM), K-nearest neighbors (KNN), and the gradient boosting machine (GBM) algorithm, to merge satellite precipitation products. In contrast, the DML algorithm is developed based on the classification RF approach and combined with these regression machine learning models (i.e., RF-RF, RF-SVM, RF-KNN, and RF-GBM). The four gridded precipitation products, including Climate Hazards Group Infra-Red Precipitation with Station (CHIRPS), Integrated Multi-Satellite Retrievals for GPM (IMERG-v06), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network-Climate Data Record (PERSIANN-CDR) and ERA-5 reanalysis datasets utilized in merging approaches. In total, we compared twelve precipitation products, including four gridded precipitation products (GPPs), four SML, and four DML, against Climate Research Unit (CRU) based rain-gauge (RG) observation. The Standardized precipitation indices (SPI) were estimated from these twelve precipitation datasets and compared their performance of CRU observation across Kenya. In addition, a total of seven statistical metrics were utilized for the performance assessment of all precipitation estimates. The results revealed that the DML merged products achieved higher accuracy (CC = 0.75–0.9) compared to SML products or other GPPs products against observational data. Also, DML merged products show higher performance (CC = 0.8–0.86) for two rainy seasons (long rain and short rain) than other GPPs, and SML merged products, except RF. Moreover, our findings indicate that the DML merged precipitation products identified major meteorological drought events with the lowest RMSE error than other precipitation products based on multiple SPI timescales (SPI-3, SPI-6, and SPI-12). The DML algorithm significantly improves SML models for precipitation estimates to monitor meteorological drought events over Kenya.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Publicly available datasets were analyzed in this study. This data can be found here: https://www.chc.ucsb.edu/data/chirps, https://sites.uea.ac.uk/cru/datahttps://www.ecmwf.int/en/forecasts/datasets/reanalysis-datasets/era-interim, https://disc.gsfc.nasa.gov/, and https://chrsdata.eng.uci.edu/. Also, Derived data supporting the finding of this study are available from the corresponding author on request.
References
Ahmed K, Sachindra DA, Shahid S, Iqbal Z, Nawaz N, Khan N (2020) Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms. Atmos Rese 236:104806. https://doi.org/10.1016/j.atmosres.2019.104806
Akinci H (2022) Assessment of rainfall-induced landslide susceptibility in Artvin, Turkey using machine learning techniques. J Afr Earth Sci 191:104535. https://doi.org/10.1016/j.jafrearsci.2022.104535
Alizadeh MR, Nikoo MR (2018) A fusion-based methodology for meteorological drought estimation using remote sensing data. Remote Sens Environ 211:229–247. https://doi.org/10.1016/j.rse.2018.04.001
Ashouri H, Hsu KL, Sorooshian S, Braithwaite DK, Knapp KR, Cecil LD, Nelson BR, Prat OP (2015) PERSIANN-CDR: daily precipitation climate data record from multisatellite observations for hydrological and climate studies. Bull Am Meteorol Soc 96(1):197–210. https://doi.org/10.1175/BAMS-D-13-00068.1
Atiah WA, Amekudzi LK, Aryee JNA, Preko K, Danuor SK (2020) Validation of satellite and merged rainfall data over Ghana, West Africa. Atmosphere 11(8):859. https://doi.org/10.3390/atmos11080859
Ayugi B, Tan G, Ullah W, Boiyo R, Ongoma V (2019) Inter-comparison of remotely sensed precipitation datasets over Kenya during 1998–2016. Atmos Res 225(1):96–109. https://doi.org/10.1016/j.atmosres.2019.03.032
Ayugi B, Tan G, Niu R, Dong Z, Ojara M, Mumo L, Babaousmail H, Ongoma V (2020) Evaluation of Meteorological Drought and Flood Scenarios over Kenya, East Africa. Atmosphere 11(3):307. https://doi.org/10.3390/atmos11030307
Barrett AB, Duivenvoorden S, Salakpi EE, Muthoka JM, Mwangi J, Oliver S, Rowhani P (2020) Forecasting vegetation condition for drought early warning systems in pastoral communities in Kenya. Remote Sens Environ 248:111886. https://doi.org/10.1016/j.rse.2020.111886
Behrangi A, Wen Y (2017) On the spatial and temporal sampling errors of remotely sensed precipitation products. Remote Sens 9(11):1127. https://doi.org/10.3390/rs9111127
Bouaziz M, Medhioub E, Csaplovisc E (2021) A machine learning model for drought tracking and forecasting using remote precipitation data and a standardized precipitation index from arid regions. J Arid Environ 189:104478. https://doi.org/10.1016/j.jaridenv.2021.104478
Breiman L (2001) Random Forest. Mach Learn 45:5–32
Chen S, Xiong L, Ma Q et al (2020) Improving daily spatial precipitation estimates by merging gauge observation with multiple satellite-based precipitation products based on the geographically weighted ridge regression method. J Hydrol 589:125156. https://doi.org/10.1016/j.jhydrol.2020.125156
Chen S, Li Q, Zhong W, Wang R, Chen D, Pan S (2022) Improved monitoring and assessment of meteorological drought based on multi-source fused precipitation data. Int J Environ Res Public Health 19(3):1542. https://doi.org/10.3390/ijerph19031542
Citakoglu H, Coskun O (2022) Comparison of hybrid machine learning methods for the prediction of short-term meteorological droughts of Sakarya Meteorological Station in Turkey. Environ Sci Pollut Res 29:75487–75511. https://doi.org/10.1007/s11356-022-21083-3
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297. https://doi.org/10.1007/BF00994018
Das P, Zhang Z, Ren H (2022a) Evaluation of four bias correction methods and random forest model for climate change projection in the Mara River Basin, East Africa. J Water Clim Change 13(4):1900. https://doi.org/10.2166/wcc.2022.299
Das P, Zhang Z, Ren H (2022b) Evaluating the accuracy of two satellite-based Quantitative Precipitation Estimation products and their application for meteorological drought monitoring over the Lake Victoria Basin, East Africa. Geo-Spatial Inf Sci 25(3):500–518. https://doi.org/10.1080/10095020.2022.2054731
de Brito CS, da Silva RM, Santos CAG, Neto RMB, Coelho VHR (2021) Monitoring meteorological drought in a semi-arid region using two long-term satellite-estimated rainfall datasets: a case study of the Piranhas River Basin, Northeastern Brazil. Atmos Res 250:105380. https://doi.org/10.1016/j.atmosres.2020.105380
Dikici M (2020) Drought Analysis with Different Indices for the Asi Basin (Turkey). Sci Rep 10(1):20739. https://doi.org/10.1038/s41598-020-77827-z
Ebrahimi-Khusfi Z, Dargahian F, Nafarzadegan AR (2022) Predicting the dust events frequency around a degraded ecosystem and determining the contribution of their controlling factors using gradient boosting-based approaches and game theory. Environ Sci Pollut Res 29(24):36655–36673. https://doi.org/10.1007/s11356-021-17265-0
Fan Z, Li W, Jiang Q, Sun W, Wen J, Gao J (2021) A comparative study of four merging approaches for regional precipitation estimation. IEEE Access 9:33625–33637. https://doi.org/10.1109/ACCESS.2021.3057057
Flah M, Nunez I, Ben Chaabene W, Nehdi ML (2021) Machine learning algorithms in civil structural health monitoring: a systematic review. Arch Computat Methods Eng 28:2621–2643. https://doi.org/10.1007/s11831-020-09471-9
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat. https://doi.org/10.1214/aos/1013203451
Funk C, Peterson P, Landsfeld M, Pedreros D, Verdin J, Shukla S, Husak G, Rowland J, Harrison L, Hoell A (2015) The climate hazards infrared precipitation with stations—a new environmental record for monitoring extremes. Sci Data 2(9):150066
Guo H, Bao A, Liu T, Chen S, Ndayisaba F (2016) Evaluation of PERSIANN-CDR for meteorological drought monitoring over China. Remote Sens 8(5):379. https://doi.org/10.3390/rs8050379
Harris I, Osborn TJ, Jones P, Lister D (2020) Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset. Sci Data 7(1):109. https://doi.org/10.1038/s41597-020-0453-3
Hastenrath S (2001) Variations of East African climate during the past two centuries. Clim Change 50:209–217
Hersbach H, Bell B, Berrisford P, Hirahara S, Horányi A, Muñoz-Sabater J, Nicolas J, Peubey C, Radu R, Schepers D, Simmons A (2020) The ERA5 global reanalysis. Q J R Meteorol Soc 146(730):1999–2049. https://doi.org/10.1002/qj.3803
Huang M, Lin R, Huang S, Xing T (2017) A novel approach for precipitation forecast via improved K-nearest neighbor algorithm. Adv Eng Inform 33:89–95. https://doi.org/10.1016/j.aei.2017.05.003
Huffman G, Bolvin D, Braithwaite D, Hsu K, Joyce R, Xie P (2014) Integrated Multi-satellitE Retrievals for GPM (IMERG), version 4.4. NASA’s Precipitation Processing Center. ftp://arthurhou.pps.eosdis.nasa.gov/gpmdata/. Accessed 31 Mar 2015
Huffman GJ, Bolvin DT, Nelkin EJ, Tan J (2019) Integrated Multi-satellitE Retrievals for GPM (IMERG) Technical Documentation. https://docserver.gesdisc.eosdis.nasa.gov/public/project/GPM/IMERG_doc.06.pdf. Accessed 18 Mar 2019
Jiang Q, Li W, Fan Z, He X, Sun W, Chen S, Wen J, Gao J, Wang J (2021) Evaluation of the ERA5 reanalysis precipitation dataset over Chinese Mainland. J Hydrol 595:125660. https://doi.org/10.1016/j.jhydrol.2020.125660
Jose DM, Vincent AM, Dwarakish GS (2022) Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques. Sci Rep 12(1):4678. https://doi.org/10.1038/s41598-022-08786-w
Kolluru V, Kolluru S, Wagle N, Acharya TD (2020) Secondary precipitation estimate merging using machine learning: development and evaluation over Krishna River Basin, India. Remote Sens 12(18):3013. https://doi.org/10.3390/rs12183013
Lai C, Zhong R, Wang Z, Wu X, Chen X, Wang P, Lian Y (2019) Monitoring hydrological drought using long-term satellite-based precipitation data. Sci Total Environ 649:1198–1208. https://doi.org/10.1016/j.scitotenv.2018.08.245
Li Q, Han X, Liu Z, He P, Shi P, Chen Q, Du F (2022) A novel information changing rate and conditional mutual information-based input feature selection method for artificial intelligence drought prediction models. Clim Dyn 58(11–12):3405–3425. https://doi.org/10.1007/s00382-021-06104-0
Liakos K, Busato P, Moshou D et al (2018) Machine learning in agriculture: a review. Sensors 18:2674. https://doi.org/10.3390/s18082674
Lin Q, Peng T, Wu Z, Guo J, Chang W, Xu Z (2022) Performance evaluation, error decomposition and Tree-based Machine Learning error correction of GPM IMERG and TRMM 3B42 products in the Three Gorges Reservoir Area. Atmos Res 268:105988. https://doi.org/10.1016/j.atmosres.2021.105988
Liu C, Yang C, Yang Q, Wang J (2021) Spatiotemporal drought analysis by the standardized precipitation index (SPI) and standardized precipitation evapotranspiration index (SPEI) in Sichuan Province. China Sci Rep 11(1):1280. https://doi.org/10.1038/s41598-020-80527-3
Macharia JM, Ngetich FK, Shisanya CA (2020) Agricultural and forest meteorology comparison of satellite remote sensing derived precipitation estimates and observed data in Kenya. Agric For Meteorol 284:107875. https://doi.org/10.1016/j.agrformet.2019.107875
Malik A, Saggi MK, Rehman S, Sajjad H, Inyurt S, Bhatia AS, Farooque AA, Oudah AY, Yaseen ZM (2022) Deep learning versus gradient boosting machine for pan evaporation prediction. Eng Appl Comput Fluid Mech 16(1):570–587. https://doi.org/10.1080/19942060.2022.2027273
Mayor Y, Tereshchenko I, Fonseca-Hernández M, Pantoja D, Montes J (2017) Evaluation of error in IMERG precipitation estimates under different topographic conditions and temporal scales over Mexico. Remote Sens 9(5):503. https://doi.org/10.3390/rs9050503
McKee TB, Doesken NJ, Kleist J (1993) The relationship of drought frequency and duration to time scales. In: The 8th Conference on Applied Climatology, Anaheim, January 17–22
Mehdizadeh S (2020) Using AR, MA, and ARMA time series models to improve the performance of MARS and KNN approaches in monthly precipitation modeling under limited climatic data. Water Resour Manage 34(1):263–282. https://doi.org/10.1007/s11269-019-02442-1
Mehr AD, Nourani V, Khosrowshahi VK, Ghorbani MA (2019) A hybrid support vector regression–firefly model for monthly rainfall forecasting. Int J Environ Sci Technol 16:335–346. https://doi.org/10.1007/s13762-018-1674-2
Miller S, Mishra V, Ellenburg WL, Adams E, Roberts J, Limaye A, Griffin R (2021) Analysis of a Short-Term and a Seasonal Precipitation Forecast over Kenya. Atmosphere 12(11):1371. https://doi.org/10.3390/atmos12111371
Mohammadi M, Farajpour A, Rastgoo A (2023) Coriolis effects on the thermo-mechanical vibration analysis of the rotating multilayer piezoelectric nanobeam. Acta Mechanica 234(2):751–774
Mohseni F, Kiani Sadr M, Eslamian S, Areffian A, Khoshfetrat A (2021) Spatial and temporal monitoring of drought conditions using the satellite rainfall estimates and remote sensing optical and thermal measurements. Adv Space Res 67(12):3942–3959. https://doi.org/10.1016/j.asr.2021.02.017
Mokhtar A, Jalali M, He H, Al-Ansari N, Elbeltagi A, Alsafadi K, Abdo HG, Sammen SS, Gyasi-Agyei Y, Rodrigo-Comino J (2021) Estimation of SPEI meteorological drought using machine learning algorithms. IEEE Access 9:65503–65523
Monego VS, Anochi JA, de Campos Velho HF (2022) South America seasonal precipitation prediction by gradient-boosting machine-learning approach. Atmosphere 13(2):243. https://doi.org/10.3390/atmos13020243
Mutsotso RB, Sichangi AW, Makokha GO (2018) Spatio-temporal drought characterization in Kenya from 1987 to 2016. Adv Remote Sens 07(02):125–143. https://doi.org/10.4236/ars.2018.72009
Ochieng P, Nyandega I, Wambua B (2022) Spatial-temporal analysis of historical and projected drought events over Isiolo County, Kenya. Theor Appl Climatol 148:531–550. https://doi.org/10.1007/s00704-022-03953-5
Ongoma V, Chen H, Omony GW (2018) Variability of extreme weather events over the equatorial East Africa, a case study of rainfall in Kenya and Uganda. Theor Appl Climatol 131(1–2):295–308. https://doi.org/10.1007/s00704-016-1973-9
Orimoloye IR, Olusola AO, Belle JA et al (2022) Drought disaster monitoring and land use dynamics: identifcation of drought drivers using regression-based algorithms. Nat Hazards 112:1085–1106. https://doi.org/10.1007/s11069-022-05219-9
Palmer WC (1965) Meteorological drought. Res. Paper No. 45, Weather Bureau, Washington, D.C., p 58
Pathak AA, Dodamani BM (2020) Comparison of Meteorological Drought Indices for Different Climatic Regions of an Indian River Basin. Asia-Pac J Atmos Sci 56(4):563–576. https://doi.org/10.1007/s13143-019-00162-5
Peel MC, Finlayson BL, Mcmahon TA (2007) Updated world map of the koppen-geiger climate classification. Hydrol Earth Syst Sci 11:1633–1644
Prodhan FA, Zhang J, Pangali Sharma TP, Nanzad L, Zhang D, Seka AM, Ahmed N, Hasan SS, Hoque MZ, Mohana HP (2022) Projection of future drought and its impact on simulated crop yield over South Asia using ensemble machine learning approach. Sci Total Environ 807:151029. https://doi.org/10.1016/j.scitotenv.2021.151029
Rahman KU, Shang S, Shahid M, Wen Y, Khan Z (2020) Application of a dynamic clustered Bayesian model averaging (DCBA) algorithm for merging multisatellite precipitation products over Pakistan. J Hydrometeorol 21(1):17–37. https://doi.org/10.1175/JHM-D-19-0087.1
Rahman KU, Shang S, Zohaib M (2021) Assessment of merged satellite precipitation datasets in monitoring meteorological drought over Pakistan. Remote Sens 13(9):1662. https://doi.org/10.3390/rs13091662
Rehman A, Chandio AA, Hussain I, Jingdong L (2019) Fertilizer consumption, water availability and credit distribution: major factors affecting agricultural productivity in Pakistan. J Saudi Soc Agric Sci 18(3):269–274. https://doi.org/10.1016/j.jssas.2017.08.002
Santos CAG, Brasil Neto RM, Nascimento doSilva daMishraFrade TVMRMMTG (2021) Geospatial drought severity analysis based on PERSIANN-CDR-estimated rainfall data for Odisha state in India (1983–2018). Sci Total Environ 750:141258. https://doi.org/10.1016/j.scitotenv.2020.141258
Sattari MT, Apaydin H, Band SS, Mosavi A, Prasad R (2021) Comparative analysis of kernel-based versus ANN and deep learning methods in monthly reference evapotranspiration estimation. Hydrol Earth Syst Sci 25(2):603–618. https://doi.org/10.5194/hess-25-603-2021
Shobeiri S, Sharafati A, Neshat A (2021) Evaluation of different gridded precipitation products in trend analysis of precipitation features over Iran. Acta Geophys 69:959–974. https://doi.org/10.1007/s11600-021-00595-5
Shrestha NK, Qamer FM, Pedreros D, Murthy MSR, Wahid SM, Shrestha M (2017) Evaluating the Accuracy of Climate Hazard Group (CHG) Satellite Rainfall Estimates for Precipitation-based Drought Monitoring in Koshi Basin, Nepal. J Hydrol Reg Stud 13:138–151. https://doi.org/10.1016/j.ejrh.2017.08.004
Song Z, Xia J, Wang G, She D, Hu C, Hong S (2022) Regionalization of hydrological model parameters using gradient boosting machine. Hydrol Earth Syst Sci 26(2):505–524. https://doi.org/10.5194/hess-26-505-2022
Taghi Sattari M, Feizi H, Samadianfard S, Falsafian K, Salwana E (2021) Estimation of monthly and seasonal precipitation: A comparative study using data-driven methods versus hybrid approach. Measurement 173:108512. https://doi.org/10.1016/j.measurement.2020.108512
Tan G, Ayugi B, Ngoma H, Ongoma V (2020) Projections of future meteorological drought events under representative concentration pathways (RCPs) of CMIP5 over Kenya, East Africa. Atmos Res 246:105112. https://doi.org/10.1016/j.atmosres.2020.105112
Wei W, Zhang J, Zhou J, Zhou L, Xie B, Li C (2021) Monitoring drought dynamics in china using optimized meteorological drought index (OMDI) based on remote sensing data sets. J Environl Manag 292:112733. https://doi.org/10.1016/j.jenvman.2021.112733
WMO (1994) Guide to hydrological practices: data acquisition and processing, analysis, forecasting and other applications, WMO 168. World Meteorological Organization, Geneva
Yaseen ZM, Ali M, Sharafati A, Al-Ansari N, Shahid S (2021) Forecasting standardized precipitation index using data intelligence models: regional investigation of Bangladesh. Sci Rep 11(1):3435. https://doi.org/10.1038/s41598-021-82977-9
Yin G, Yoshikane T, Yamamoto K, Kubota T, Yoshimura K (2022) A support vector machine-based method for improving real-time hourly precipitation forecast in Japan. J Hydrol 612:128125. https://doi.org/10.1016/j.jhydrol.2022.128125
Yoosefdoost I, Khashei-Siuki A, Tabari H, Mohammadrezapour O (2022) Runoff simulation under future climate change conditions: performance comparison of data-mining algorithms and conceptual models. Water Resour Manag 36(4):1191–1215. https://doi.org/10.1007/s11269-022-03068-6
Yumnam K, Guntu RK, Rathinasamy M, Agarwal A (2022) Quantile-based bayesian model averaging approach towards merging of precipitation products. J Hydrol 604:14. https://doi.org/10.1016/j.jhydrol.2021.127206
Zandi O, Zahraie B, Nasseri M, Behrangi A (2022) Stacking machine learning models versus a locally weighted linear model to generate high-resolution monthly precipitation over a topographically complex area. Atmos Res 272:106159. https://doi.org/10.1016/j.atmosres.2022.106159
Zandi O, Nasseri M, Zahraie B (2023) A locally weighted linear ridge regression framework for spatial interpolation of monthly precipitation over an orographically complex area. Int J Climatol 43:2601–2622. https://doi.org/10.1002/joc.7992
Zhang Y, Li Z (2020) Uncertainty analysis of standardized precipitation index due to the effects of probability distributions and parameter errors. Front Earth Sci 8:76. https://doi.org/10.3389/feart.2020.00076
Zhang R, Chen ZY, Xu LJ, Ou CQ (2019) Meteorological drought forecasting based on a statistical model with machine learning techniques in Shaanxi province, China. Sci Total Environ 665(2019):338–346. https://doi.org/10.1016/j.scitotenv.2019.01.431
Zhang L, Li X, Zheng D, Zhang K, Ma Q, Zhao Y, Ge Y (2021a) Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach. J Hydrol 594:125969. https://doi.org/10.1016/j.jhydrol.2021.125969
Zhang W, Li H, Li Y et al (2021b) Application of deep learning algorithms in geotechnical engineering: a short critical review. Artif Intell Rev 54:5633–5673. https://doi.org/10.1007/s10462-021-09967-
Zhang Z-C, Zeng X-M, Li G, Lu B, Xiao M-Z, Wang B-Z (2022) Summer precipitation forecast using an optimized artificial neural network with a genetic algorithm for Yangtze-Huaihe River Basin, China. Atmosphere 13(6):929. https://doi.org/10.3390/atmos13060929
Zhao H, Ma Y (2019) Evaluating the drought-monitoring utility of four satellite-based quantitative precipitation estimation products at global scale. Remote Sens 11(17):2010. https://doi.org/10.3390/rs11172010
Zhong R, Chen X, Lai C, Wang Z, Lian Y, Yu H, Wu X (2019) Drought monitoring utility of satellite-based precipitation products across Mainland China. J Hydrol 568:343–359. https://doi.org/10.1016/j.jhydrol.2018.10.072
Funding
This research received no specific grant from any funding agency.
Author information
Authors and Affiliations
Contributions
SG, JL, and PD designed the paper. SG conducted the data processing and statistical analysis and wrote the paper. PD and JL made great efforts in writing and figure optimization. ZZ made a great effort for editing the manuscript. All the authors contributed to the paper. All authors have read and agreed to the publication of the present version of the manuscript.
Corresponding authors
Ethics declarations
Conflict of interest
No potential conflict of interest was reported by the author(s).
Ethical Approval
All the work complies with Ethical standards.
Consent of Participate
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ghosh, S., Lu, J., Das, P. et al. Machine learning algorithms for merging satellite-based precipitation products and their application on meteorological drought monitoring over Kenya. Clim Dyn 62, 141–163 (2024). https://doi.org/10.1007/s00382-023-06893-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00382-023-06893-6