Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura

The diel variation of water temperatures is crucial information for lakes. This study investigated such variation in Lake Kasumigaura, the second largest lake in Japan, situated 60 km from the Tokyo metropolitan area, utilizing high-frequency monitoring and deep learning techniques. Data from high-f...

Full description

Saved in:
Bibliographic Details
Main Authors: Senlin Zhu, Ryuichiro Shinohara, Shin–Ichiro S. Matsuzaki, Ayato Kohzu, Mirai Watanabe, Megumi Nakagawa, Fabio Di Nunno, Jiang Sun, Quan Zhou, Francesco Granata
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X24014158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121332741242880
author Senlin Zhu
Ryuichiro Shinohara
Shin–Ichiro S. Matsuzaki
Ayato Kohzu
Mirai Watanabe
Megumi Nakagawa
Fabio Di Nunno
Jiang Sun
Quan Zhou
Francesco Granata
author_facet Senlin Zhu
Ryuichiro Shinohara
Shin–Ichiro S. Matsuzaki
Ayato Kohzu
Mirai Watanabe
Megumi Nakagawa
Fabio Di Nunno
Jiang Sun
Quan Zhou
Francesco Granata
author_sort Senlin Zhu
collection DOAJ
description The diel variation of water temperatures is crucial information for lakes. This study investigated such variation in Lake Kasumigaura, the second largest lake in Japan, situated 60 km from the Tokyo metropolitan area, utilizing high-frequency monitoring and deep learning techniques. Data from high-frequency monitoring of vertical water temperatures at seven depths were employed. A convolutional neural network (CNN) based deep learning model was developed and assessed across three input scenarios. The impact of forecast horizons ranging from one to 48 h ahead on model performance was examined. Results indicate a degradation in model performance with increasing forecast horizons, irrespective of input scenario or water depth. Notably, the CNN model demonstrates superior performance in near-term and medium-term forecasts compared to long-term predictions, underscoring the need for enhanced efforts in long-term forecasting. Overall, the CNN model effectively reproduces vertical water temperature profiles and captures diel variations in lake water temperatures. Incorporating additional input variables does not necessarily improve model performance; however, using surface water temperatures and air temperatures as inputs produces acceptable results for modeling vertical temperature profiles. These findings have implications for lake management in Lake Kasumigaura (e.g., controlling phytoplankton and zooplankton communities) and offer insights into water temperature modeling for other lakes.
format Article
id doaj-art-884954ca26b542ed931fd28c597430e1
institution Kabale University
issn 1470-160X
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-884954ca26b542ed931fd28c597430e12024-12-16T05:35:42ZengElsevierEcological Indicators1470-160X2024-12-01169112958Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake KasumigauraSenlin Zhu0Ryuichiro Shinohara1Shin–Ichiro S. Matsuzaki2Ayato Kohzu3Mirai Watanabe4Megumi Nakagawa5Fabio Di Nunno6Jiang Sun7Quan Zhou8Francesco Granata9College of Hydraulic Science and Engineering, Yangzhou University, Yangzhou, China; Corresponding author.National Institute for Environmental Studies, JapanNational Institute for Environmental Studies, JapanNational Institute for Environmental Studies, JapanNational Institute for Environmental Studies, JapanNational Institute for Environmental Studies, JapanDepartment of Civil and Mechanical Engineering (DICEM), University of Cassino and Southern Lazio, Via Di Biasio, 43, 03043 Cassino, Frosinone, ItalyCollege of Hydraulic Science and Engineering, Yangzhou University, Yangzhou, ChinaCollege of Hydraulic Science and Engineering, Yangzhou University, Yangzhou, ChinaDepartment of Civil and Mechanical Engineering (DICEM), University of Cassino and Southern Lazio, Via Di Biasio, 43, 03043 Cassino, Frosinone, ItalyThe diel variation of water temperatures is crucial information for lakes. This study investigated such variation in Lake Kasumigaura, the second largest lake in Japan, situated 60 km from the Tokyo metropolitan area, utilizing high-frequency monitoring and deep learning techniques. Data from high-frequency monitoring of vertical water temperatures at seven depths were employed. A convolutional neural network (CNN) based deep learning model was developed and assessed across three input scenarios. The impact of forecast horizons ranging from one to 48 h ahead on model performance was examined. Results indicate a degradation in model performance with increasing forecast horizons, irrespective of input scenario or water depth. Notably, the CNN model demonstrates superior performance in near-term and medium-term forecasts compared to long-term predictions, underscoring the need for enhanced efforts in long-term forecasting. Overall, the CNN model effectively reproduces vertical water temperature profiles and captures diel variations in lake water temperatures. Incorporating additional input variables does not necessarily improve model performance; however, using surface water temperatures and air temperatures as inputs produces acceptable results for modeling vertical temperature profiles. These findings have implications for lake management in Lake Kasumigaura (e.g., controlling phytoplankton and zooplankton communities) and offer insights into water temperature modeling for other lakes.http://www.sciencedirect.com/science/article/pii/S1470160X24014158Thermal dynamicsDiel variationHigh-frequency monitoringDeep modelingClimate change
spellingShingle Senlin Zhu
Ryuichiro Shinohara
Shin–Ichiro S. Matsuzaki
Ayato Kohzu
Mirai Watanabe
Megumi Nakagawa
Fabio Di Nunno
Jiang Sun
Quan Zhou
Francesco Granata
Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
Ecological Indicators
Thermal dynamics
Diel variation
High-frequency monitoring
Deep modeling
Climate change
title Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
title_full Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
title_fullStr Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
title_full_unstemmed Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
title_short Diel temperature patterns unveiled: High-frequency monitoring and deep learning in Lake Kasumigaura
title_sort diel temperature patterns unveiled high frequency monitoring and deep learning in lake kasumigaura
topic Thermal dynamics
Diel variation
High-frequency monitoring
Deep modeling
Climate change
url http://www.sciencedirect.com/science/article/pii/S1470160X24014158
work_keys_str_mv AT senlinzhu dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT ryuichiroshinohara dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT shinichirosmatsuzaki dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT ayatokohzu dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT miraiwatanabe dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT meguminakagawa dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT fabiodinunno dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT jiangsun dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT quanzhou dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura
AT francescogranata dieltemperaturepatternsunveiledhighfrequencymonitoringanddeeplearninginlakekasumigaura