Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes

Analysis of hydro-climatological time series and spatiotemporal dynamics of meteorological variables has become critical in the context of climate change, especially in Southern African countries where rain-fed agriculture is predominant. In this work, we compared modern unsupervised time series and...

Full description

Bibliographic Details
Main Authors: Chipindu, Lovemore, Mupangwa, Walter, Nyagumbo, Isaiah, Zaman-Allah, Mainassara
Format: Journal Article
Language:Inglés
Published: Wiley 2023
Subjects:
Online Access:https://hdl.handle.net/10568/137166
_version_ 1855523351552851968
author Chipindu, Lovemore
Mupangwa, Walter
Nyagumbo, Isaiah
Zaman-Allah, Mainassara
author_browse Chipindu, Lovemore
Mupangwa, Walter
Nyagumbo, Isaiah
Zaman-Allah, Mainassara
author_facet Chipindu, Lovemore
Mupangwa, Walter
Nyagumbo, Isaiah
Zaman-Allah, Mainassara
author_sort Chipindu, Lovemore
collection Repository of Agricultural Research Outputs (CGSpace)
description Analysis of hydro-climatological time series and spatiotemporal dynamics of meteorological variables has become critical in the context of climate change, especially in Southern African countries where rain-fed agriculture is predominant. In this work, we compared modern unsupervised time series and segmentation approaches and commonly used time series models to analyse rainfall regime changes in the coastal, sub-humid and semi-arid regions of Southern Africa. Rainfall regimes change modelling and prediction inform farming strategies especially when choosing measures for mixed crop–livestock farming systems, as farmers can decide to do rainwater harvesting and moisture conservation or supplementary irrigation if water resources are available. The main goal of this study was to predict/identify rainfall cluster trends over time using regression with hidden logistic process (RHLP) or hidden Markov model regression (HMMR) supplemented by autoregressive integrated moving average (ARIMA) and Facebook Prophet models. Historical time series rainfall data was sourced from meteorological services departments for selected site over an average period of 55 years. Commonly used approaches forecasted an upward rainfall trend in the coastal and sub-humid regions and a declining trend in semi-arid areas with high variability between and within seasons. For all sites, Ljung-Box Test Statistics suggested the existence of autocorrelation in rainfall time series data. Prediction capabilities were investigated using the root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) which indicated not much difference between ARIMA and Facebook Prophet models. RHLP and HMMR offered a unique clustering and segmentation approach examining between and within-season rainfall variability. A maximum of 20 unique rainfall clusters with similar trend characteristics were determined as going beyond this brought non-significant difference to regime changes. A clear trend was exhibited from 1980 going backwards as compared to recent years signifying how unpredictable is rainfall in Southern Africa. The unsupervised approaches predicted a clear cluster trend in coastal than in sub-humid and semi-arid and the performance was assessed using Akaike information criteria and log-likelihood which showed improvement in prediction power as the number of segmentation clusters approaches 20.
format Journal Article
id CGSpace137166
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Wiley
publisherStr Wiley
record_format dspace
spelling CGSpace1371662025-02-19T13:49:59Z Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes Chipindu, Lovemore Mupangwa, Walter Nyagumbo, Isaiah Zaman-Allah, Mainassara coastal areas semiarid zones subhumid zones rainfall climate change Analysis of hydro-climatological time series and spatiotemporal dynamics of meteorological variables has become critical in the context of climate change, especially in Southern African countries where rain-fed agriculture is predominant. In this work, we compared modern unsupervised time series and segmentation approaches and commonly used time series models to analyse rainfall regime changes in the coastal, sub-humid and semi-arid regions of Southern Africa. Rainfall regimes change modelling and prediction inform farming strategies especially when choosing measures for mixed crop–livestock farming systems, as farmers can decide to do rainwater harvesting and moisture conservation or supplementary irrigation if water resources are available. The main goal of this study was to predict/identify rainfall cluster trends over time using regression with hidden logistic process (RHLP) or hidden Markov model regression (HMMR) supplemented by autoregressive integrated moving average (ARIMA) and Facebook Prophet models. Historical time series rainfall data was sourced from meteorological services departments for selected site over an average period of 55 years. Commonly used approaches forecasted an upward rainfall trend in the coastal and sub-humid regions and a declining trend in semi-arid areas with high variability between and within seasons. For all sites, Ljung-Box Test Statistics suggested the existence of autocorrelation in rainfall time series data. Prediction capabilities were investigated using the root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) which indicated not much difference between ARIMA and Facebook Prophet models. RHLP and HMMR offered a unique clustering and segmentation approach examining between and within-season rainfall variability. A maximum of 20 unique rainfall clusters with similar trend characteristics were determined as going beyond this brought non-significant difference to regime changes. A clear trend was exhibited from 1980 going backwards as compared to recent years signifying how unpredictable is rainfall in Southern Africa. The unsupervised approaches predicted a clear cluster trend in coastal than in sub-humid and semi-arid and the performance was assessed using Akaike information criteria and log-likelihood which showed improvement in prediction power as the number of segmentation clusters approaches 20. 2023 2024-01-04T16:10:48Z 2024-01-04T16:10:48Z Journal Article https://hdl.handle.net/10568/137166 en Open Access application/pdf Wiley Chipindu, L., Mupangwa, W., Nyagumbo, I., & Zaman‐Allah, M. (2023). Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes. Geoscience Data Journal, gdj3.228.
spellingShingle coastal areas
semiarid zones
subhumid zones
rainfall
climate change
Chipindu, Lovemore
Mupangwa, Walter
Nyagumbo, Isaiah
Zaman-Allah, Mainassara
Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title_full Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title_fullStr Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title_full_unstemmed Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title_short Unsupervised segmentation and clustering time series approach to Southern Africa rainfall regime changes
title_sort unsupervised segmentation and clustering time series approach to southern africa rainfall regime changes
topic coastal areas
semiarid zones
subhumid zones
rainfall
climate change
url https://hdl.handle.net/10568/137166
work_keys_str_mv AT chipindulovemore unsupervisedsegmentationandclusteringtimeseriesapproachtosouthernafricarainfallregimechanges
AT mupangwawalter unsupervisedsegmentationandclusteringtimeseriesapproachtosouthernafricarainfallregimechanges
AT nyagumboisaiah unsupervisedsegmentationandclusteringtimeseriesapproachtosouthernafricarainfallregimechanges
AT zamanallahmainassara unsupervisedsegmentationandclusteringtimeseriesapproachtosouthernafricarainfallregimechanges