2026-09-20T14:53:03Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1519322023-08-24T03:45:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Terrer, César
Chen, Minghao
Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
2023-08-23T16:19:58Z
2023-08-23T16:19:58Z
2023-06
2023-06-22T14:48:53.100Z
https://hdl.handle.net/1721.1/151932
https://orcid.org/0000-0001-8936-975X
This study investigated the impact of interannual precipitation variability on above-ground terrestrial ecosystem productivity in the Hulunbuir ecosystem, using time series analysis, regression analysis, and machine learning models. The study's primary goal was to enhance our understanding of the effects of precipitation variability on ecosystems and develop practical solutions for promoting ecosystem sustainability and adaptability under changing climate conditions. The study analyzed trends and patterns of interannual precipitation variability within the study area, investigated the historic relationship between precipitation and ecosystem productivity using regression analysis, developed and compared machine learning models to predict the impact of interannual precipitation variability on ecosystem productivity, evaluated model performance, and provided insights into the mechanisms underlying the impacts of interannual precipitation variability on ecosystem productivity. The findings of this study suggested that precipitation is an important driver of vegetation productivity in the Hulunbuir ecosystem, and the machine learning models, particularly LSTM and CNN models, were found to be effective in predicting NPP in different ecosystems. The study's findings can inform ecosystem-specific management strategies to optimize productivity and resilience to environmental change, as well as policy decisions regarding the sustainable use of natural resources and the mitigation of climate change impacts.
Keywords: interannual precipitation variability, terrestrial ecosystem productivity, time series
analysis, machine learning models, climate change impacts.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Investigating the Influence of Interannual Precipitation Variability on Terrestrial Ecosystem Productivity
Thesis
application/pdf
Master
Master of Engineering in Civil and Environmental Engineering
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="37b49631-4799-44b4-a77c-585f6651e7d9">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Investigating the Influence of Interannual Precipitation Variability on Terrestrial Ecosystem Productivity</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Chen, Minghao</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>This study investigated the impact of interannual precipitation variability on above-ground terrestrial ecosystem productivity in the Hulunbuir ecosystem, using time series analysis, regression analysis, and machine learning models. The study's primary goal was to enhance our understanding of the effects of precipitation variability on ecosystems and develop practical solutions for promoting ecosystem sustainability and adaptability under changing climate conditions. The study analyzed trends and patterns of interannual precipitation variability within the study area, investigated the historic relationship between precipitation and ecosystem productivity using regression analysis, developed and compared machine learning models to predict the impact of interannual precipitation variability on ecosystem productivity, evaluated model performance, and provided insights into the mechanisms underlying the impacts of interannual precipitation variability on ecosystem productivity. The findings of this study suggested that precipitation is an important driver of vegetation productivity in the Hulunbuir ecosystem, and the machine learning models, particularly LSTM and CNN models, were found to be effective in predicting NPP in different ecosystems. The study's findings can inform ecosystem-specific management strategies to optimize productivity and resilience to environmental change, as well as policy decisions regarding the sustainable use of natural resources and the mitigation of climate change impacts.
Keywords: interannual precipitation variability, terrestrial ecosystem productivity, time series
analysis, machine learning models, climate change impacts.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>