Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps
Aboveground biomass (AGB) is an important forest attribute directly linked to the forest carbon pool. The use of satellite remote sensing (RS) data has increased for AGB prediction due to their large footprint and low-cost availability. However, they have been limited due to saturation effect that l...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9785720/ |
| _version_ | 1811333678845919232 |
|---|---|
| author | Parth Naik Michele Dalponte Lorenzo Bruzzone |
| author_facet | Parth Naik Michele Dalponte Lorenzo Bruzzone |
| author_sort | Parth Naik |
| collection | DOAJ |
| description | Aboveground biomass (AGB) is an important forest attribute directly linked to the forest carbon pool. The use of satellite remote sensing (RS) data has increased for AGB prediction due to their large footprint and low-cost availability. However, they have been limited due to saturation effect that leads to low prediction precision. In this article, we propose an innovative and dynamic architecture based on generative neural network that extracts target oriented generative features for predicting forest AGB using satellite RS data. These features are more resilient to mixed forest types and geographical conditions as compared to the traditional features and models. The effectiveness of the proposed features was assessed by experiments performed using multispectral, synthetic aperture radar, and combined dual-source datasets. The proposed model achieved best performance in terms of precision, model agreement, and overfitting as compared to the other conventional models for all analyzed datasets. The t-distributed stochastic neighbor embedding scatterplots of the generative features clearly show one dimension of the feature space associated with the target AGB. Feature importance analysis indicated that the produced generative features were more significant than the conventional analytical features. Also, the model provided a robust framework for homogeneous fusion of multisensor features from satellite RS data for predicting AGB. |
| first_indexed | 2024-04-13T16:56:31Z |
| format | Article |
| id | doaj.art-184ae11324ff40898582d51408bb9d6f |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-13T16:56:31Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-184ae11324ff40898582d51408bb9d6f2022-12-22T02:38:48ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01154755477110.1109/JSTARS.2022.31790279785720Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian AlpsParth Naik0https://orcid.org/0000-0001-9399-1103Michele Dalponte1https://orcid.org/0000-0001-9850-8985Lorenzo Bruzzone2https://orcid.org/0000-0002-6036-459XDepartment of Information Engineering and Computer Science, University of Trento, Trento, ItalyResearch and Innovation Center, Fondazione Edmund Mach, San Michele all'Adige, ItalyDepartment of Information Engineering and Computer Science, University of Trento, Trento, ItalyAboveground biomass (AGB) is an important forest attribute directly linked to the forest carbon pool. The use of satellite remote sensing (RS) data has increased for AGB prediction due to their large footprint and low-cost availability. However, they have been limited due to saturation effect that leads to low prediction precision. In this article, we propose an innovative and dynamic architecture based on generative neural network that extracts target oriented generative features for predicting forest AGB using satellite RS data. These features are more resilient to mixed forest types and geographical conditions as compared to the traditional features and models. The effectiveness of the proposed features was assessed by experiments performed using multispectral, synthetic aperture radar, and combined dual-source datasets. The proposed model achieved best performance in terms of precision, model agreement, and overfitting as compared to the other conventional models for all analyzed datasets. The t-distributed stochastic neighbor embedding scatterplots of the generative features clearly show one dimension of the feature space associated with the target AGB. Feature importance analysis indicated that the produced generative features were more significant than the conventional analytical features. Also, the model provided a robust framework for homogeneous fusion of multisensor features from satellite RS data for predicting AGB.https://ieeexplore.ieee.org/document/9785720/Aboveground biomass (AGB)feature extractionfeature fusiongenerative featuresvariational autoencoder |
| spellingShingle | Parth Naik Michele Dalponte Lorenzo Bruzzone Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aboveground biomass (AGB) feature extraction feature fusion generative features variational autoencoder |
| title | Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps |
| title_full | Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps |
| title_fullStr | Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps |
| title_full_unstemmed | Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps |
| title_short | Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps |
| title_sort | generative feature extraction from sentinel 1 and 2 data for prediction of forest aboveground biomass in the italian alps |
| topic | Aboveground biomass (AGB) feature extraction feature fusion generative features variational autoencoder |
| url | https://ieeexplore.ieee.org/document/9785720/ |
| work_keys_str_mv | AT parthnaik generativefeatureextractionfromsentinel1and2dataforpredictionofforestabovegroundbiomassintheitalianalps AT micheledalponte generativefeatureextractionfromsentinel1and2dataforpredictionofforestabovegroundbiomassintheitalianalps AT lorenzobruzzone generativefeatureextractionfromsentinel1and2dataforpredictionofforestabovegroundbiomassintheitalianalps |