2026-10-11T18:37:47Z
https://api.figshare.com/v2/oai
oai:figshare.com:article/33988342
2026-09-24T17:35:57Z
category_8
category_272
category_39
category_734
category_931
category_106
portal_5
item_type_3
month_year_09_2026
<p>Model evaluation metrics.</p>
Saadatu Umaru Baba (25105195)
Abu-hanifa Babati (25105198)
Zaharaddeen Isa (25105201)
Microbiology
Environmental Sciences not elsewhere classified
Ecology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Science Policy
nigerian meteorological agency
modified mann kendall
inverse distance weighting
innovative trend analysis
historical meteorological data
whereas temporal trends
div >< p
predict heatwave trends
lstm based forecasting
heatwave trends
based model
heatwave intensity
testing phase
term memory
study aimed
spatial variation
relative humidity
pronounced increase
northwestern nigeria
nimet ).
minimum temperature
mapped via
lstm models
long short
ita ).
findings revealed
findings demonstrate
climate change
analyzed via
agricultural productivity
<div><p>Climate change has accelerated devastating impacts across the globe, and heatwaves are among the most severe climate extremes threatening human health, agricultural productivity, and ecosystems in northwestern Nigeria. This study aimed to develop a long short-term memory (LSTM) based model to predict heatwave trends in northwestern Nigeria. Historical meteorological data, including daily maximum temperature, minimum temperature, and relative humidity from 1980 to 2024, were sourced from the Nigerian Meteorological Agency (NiMet). Heatwave intensity was measured via heat index (HI) computation, whereas temporal trends were analyzed via the Modified Mann Kendall (MMK) test and Innovative Trend Analysis (ITA). Spatial variation in heatwave intensity was mapped via the Inverse Distance Weighting (IDW) method. The LSTM model demonstrated high predictive accuracy during the testing phase, with correlation coefficients (R) ranging from 0.87 to 0.91 and coefficients of determination (R<sup>2</sup>) ranging from 0.76 to 0.83. The findings revealed a pronounced increase in the frequency and severity of heatwaves across northwestern Nigeria. These findings demonstrate the ability of LSTM based forecasting to provide reliable heatwave predictions and highlight the potential of LSTM models for supporting regional climate adaptation strategies, heat early warning systems, and evidence-based decision making.</p></div>
2026-09-24T17:35:35Z
Dataset
Dataset
10.1371/journal.pclm.0001005.t004
https://figshare.com/articles/dataset/_p_Model_evaluation_metrics_p_/33988342
CC BY 4.0