Scholarlink

<p>Algal blooms pose significant threats to marine ecosystems and human health. Accurate forecasting of chlorophyll-<i>a</i> (Chl-<i>a</i>) concentration is critical for effective control of harmful algal blooms (HABs). This study proposes a novel approach for enhancing Chl-<i>a</i> concentration forecasting by integrating the AdaBoost algorithm with long short-term memory (LSTM) neural networks. We developed a strong forecasting model by combining adaptive boosting (AdaBoost) with LSTM models in Xiamen Bay, China. This model achieved higher correlation coefficients and lower root mean square errors than individual weak models. The AdaBoost-optimized model increased the frequency of low absolute errors while decreasing the occurrence of high absolute errors, which indicated improved overall prediction accuracy and reliability. Moreover, the model effectively reduced performance fluctuations, which are frequent in deep learning models. The application of a non-uniform initial weighting scheme within the AdaBoost framework further enhanced model performance for high Chl-<i>a</i> concentration values, which are critical for detecting HABs. The optimization effect of AdaBoost was validated by applying it to data collected from the Ningde area. A robust framework is provided in this study to improve Chl-<i>a</i> concentration predictions and offer valuable insights for managing coastal ecosystems facing the challenges of algal blooms.</p>

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

Enhanced forecasting of coastal chlorophyll-a through AdaBoost-optimized LSTM models

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • Wenxiang Ding,
  • Caiyun Zhang,
  • Xueding Li,
  • Liyu Zhang,
  • Nengwang Chen

摘要

Algal blooms pose significant threats to marine ecosystems and human health. Accurate forecasting of chlorophyll-a (Chl-a) concentration is critical for effective control of harmful algal blooms (HABs). This study proposes a novel approach for enhancing Chl-a concentration forecasting by integrating the AdaBoost algorithm with long short-term memory (LSTM) neural networks. We developed a strong forecasting model by combining adaptive boosting (AdaBoost) with LSTM models in Xiamen Bay, China. This model achieved higher correlation coefficients and lower root mean square errors than individual weak models. The AdaBoost-optimized model increased the frequency of low absolute errors while decreasing the occurrence of high absolute errors, which indicated improved overall prediction accuracy and reliability. Moreover, the model effectively reduced performance fluctuations, which are frequent in deep learning models. The application of a non-uniform initial weighting scheme within the AdaBoost framework further enhanced model performance for high Chl-a concentration values, which are critical for detecting HABs. The optimization effect of AdaBoost was validated by applying it to data collected from the Ningde area. A robust framework is provided in this study to improve Chl-a concentration predictions and offer valuable insights for managing coastal ecosystems facing the challenges of algal blooms.