Modeling and large-scale mapping of forest above-ground biomass AGB) is a complicated, challenging, and expensive task. There are considerable variations in forest characteristics that create functional disparity for different models and needs comprehensive evaluation. Moreover, the human-bias involved in the process of modeling and evaluation affects the generalization of models at larger scales. In this article, we present an automated-machine learning framework for modeling, evaluation, and stacking of multiple base models for AGB prediction. We incorporate a hyper-parameter optimization procedure for automatic extraction of targeted features from multitemporal Sentinel-2 data that minimizes human-bias in the proposed modeling pipeline. We integrate the two independent frameworks for automatic feature extraction and automatic model ensembling and evaluation. The results suggest that the extracted target-oriented features have an excessive contribution of red-edge and short-wave infrared spectrum. The feature importance scale indicates a dominant role of summer-based features as compared to other seasons. The automated ensembling and evaluation framework produced a stacked ensemble of base models that outperformed individual base models in accurately predicting forest AGB. The stacked ensemble model delivered the best scores of R-cv(2) = 0.71 and RMSE = 74.44 Mg ha(-1). The other base models delivered R-cv(2) and RMSE ranging between 0.38-0.66 and 81.27-109.44 Mg ha(-1), respectively. The model evaluation metrics indicated that the stacked ensemble model was more resistant to outliers and achieved a better generalization. Thus, the proposed study demonstrated an effective automated modeling pipeline for predicting AGB by minimizing human-bias and deployable over large and diverse forest areas.

Automated Machine Learning Driven Stacked Ensemble Modeling for Forest Aboveground Biomass Prediction Using Multitemporal Sentinel-2 Data / Naik, Parth; Dalponte, Michele; Bruzzone, Lorenzo. - In: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING. - ISSN 1939-1404. - 16:(2023), pp. 3442-3454. [10.1109/JSTARS.2022.3232583]

Automated Machine Learning Driven Stacked Ensemble Modeling for Forest Aboveground Biomass Prediction Using Multitemporal Sentinel-2 Data

Parth Naik;Michele Dalponte;Lorenzo Bruzzone
2023-01-01

Abstract

Modeling and large-scale mapping of forest above-ground biomass AGB) is a complicated, challenging, and expensive task. There are considerable variations in forest characteristics that create functional disparity for different models and needs comprehensive evaluation. Moreover, the human-bias involved in the process of modeling and evaluation affects the generalization of models at larger scales. In this article, we present an automated-machine learning framework for modeling, evaluation, and stacking of multiple base models for AGB prediction. We incorporate a hyper-parameter optimization procedure for automatic extraction of targeted features from multitemporal Sentinel-2 data that minimizes human-bias in the proposed modeling pipeline. We integrate the two independent frameworks for automatic feature extraction and automatic model ensembling and evaluation. The results suggest that the extracted target-oriented features have an excessive contribution of red-edge and short-wave infrared spectrum. The feature importance scale indicates a dominant role of summer-based features as compared to other seasons. The automated ensembling and evaluation framework produced a stacked ensemble of base models that outperformed individual base models in accurately predicting forest AGB. The stacked ensemble model delivered the best scores of R-cv(2) = 0.71 and RMSE = 74.44 Mg ha(-1). The other base models delivered R-cv(2) and RMSE ranging between 0.38-0.66 and 81.27-109.44 Mg ha(-1), respectively. The model evaluation metrics indicated that the stacked ensemble model was more resistant to outliers and achieved a better generalization. Thus, the proposed study demonstrated an effective automated modeling pipeline for predicting AGB by minimizing human-bias and deployable over large and diverse forest areas.
2023
Naik, Parth; Dalponte, Michele; Bruzzone, Lorenzo
Automated Machine Learning Driven Stacked Ensemble Modeling for Forest Aboveground Biomass Prediction Using Multitemporal Sentinel-2 Data / Naik, Parth; Dalponte, Michele; Bruzzone, Lorenzo. - In: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING. - ISSN 1939-1404. - 16:(2023), pp. 3442-3454. [10.1109/JSTARS.2022.3232583]
File in questo prodotto:
File Dimensione Formato  
Automated_Machine_Learning_Driven_Stacked_Ensemble_Modeling_for_Forest_Aboveground_Biomass_Prediction_Using_Multitemporal_Sentinel-2_Data.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 10.01 MB
Formato Adobe PDF
10.01 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/400192
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact