Scholarlink

Accurate climatic variable prediction is crucial to assess and regulate climate variability-affected wetland ecosystems. The Seasonal Autoregressive Integrated Moving Average (SARIMA) model is employed in this study to predict monthly temperature, humidity, and precipitation patterns in the Karaivetti Wetland, Tamil Nadu, using 2010–2020 climate data. The stationarity of the time series was established by the Augmented Dickey-Fuller (ADF) test. Model performance was evaluated by the Autocorrelation Function (ACF), Partial Autocorrelation Function (PACF), residual diagnostics, and Root Mean Square Error (RMSE). The SARIMA model was able to identify the seasonal climatic trends, where there was a general increase in temperature during the pre- and post-monsoon periods and a considerable decline in precipitation, especially during the Southwest monsoon. These findings point towards changing climate trends that can potentially influence the wetland ecological balance. Though this the inquiry is focused to climatic forecast, the outcomes make a robust foundation for later research into environmental impacts and ecosystem response. This approach has the potential to help climate-informed decision-making for conservation and management of wetlands based on on-going climate change.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Forecasting Climatic Variables for Wetland Ecosystem Assessment in Karaivetti Using Seasonal ARIMA Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Thylashri,
  • S. Ravikumar,
  • G. Yazhini

摘要

Accurate climatic variable prediction is crucial to assess and regulate climate variability-affected wetland ecosystems. The Seasonal Autoregressive Integrated Moving Average (SARIMA) model is employed in this study to predict monthly temperature, humidity, and precipitation patterns in the Karaivetti Wetland, Tamil Nadu, using 2010–2020 climate data. The stationarity of the time series was established by the Augmented Dickey-Fuller (ADF) test. Model performance was evaluated by the Autocorrelation Function (ACF), Partial Autocorrelation Function (PACF), residual diagnostics, and Root Mean Square Error (RMSE). The SARIMA model was able to identify the seasonal climatic trends, where there was a general increase in temperature during the pre- and post-monsoon periods and a considerable decline in precipitation, especially during the Southwest monsoon. These findings point towards changing climate trends that can potentially influence the wetland ecological balance. Though this the inquiry is focused to climatic forecast, the outcomes make a robust foundation for later research into environmental impacts and ecosystem response. This approach has the potential to help climate-informed decision-making for conservation and management of wetlands based on on-going climate change.