EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

Marko Pavlovic, Slobodan Ilic, Neobojša Ralevic, Nenad Antonic, Dylan Warren Raffa, Michele Bandecchi, Dubravko Culibrk

Remote Sensing · 10.02.2024 · 16 (4) · 655

DOI: 10.3390/rs16040655 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.02.2024. Verfasst von Marko Pavlovic und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive soil sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) for segmentation, as well as satellite imagery, to estimate the SOC remotely. We propose a new two-stage pipeline for remote SOC estimation, which relies on using a DNN trained to classify land cover to perform feature extraction, while the SOC estimation is performed by a different ML model. The first stage is an image segmentation DNN with the U-Net architecture, which is trained to estimate the land cover for an observed geographical region, based on multi-spectral images taken by the Sentinel-2 satellite constellation. This estimator is subsequently used to extract the latent feature vector for each of the output pixels, by rolling back from the output (dense) layer of the U-Net and accessing the last available convolutional layer of the same dimension as our desired output. The second stage is trained on a set of feature vectors extracted at the coordinates for which manual SOC measurements exist. We tested a variety of ML models and report on their performance. Using the best extremely randomized trees model, we generated a spatially continuous map of SOC estimations for the region of Tuscany, in Italy, with a resolution of 10 m, to share with the researchers as a means of validating the results and to demonstrate the efficiency of the proposed approach, which can can easily be scaled to create a global continuous SOC map.

Zitieren

APA

Pavlovic, M., Ilic, S., Ralevic, N., Antonic, N., Raffa, D. W., Bandecchi, M., & Culibrk, D. (2024). A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing. Remote Sensing, 16(4), 655. https://doi.org/10.3390/rs16040655

Vancouver

Pavlovic M, Ilic S, Ralevic N, Antonic N, Raffa DW, Bandecchi M, et al. A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing. Remote Sensing. 2024;16(4):655. doi:10.3390/rs16040655

BibTeX
@article{Pavlovic2024,
  author = {Pavlovic, Marko and Ilic, Slobodan and Ralevic, Neobojša and Antonic, Nenad and Raffa, Dylan Warren and Bandecchi, Michele and Culibrk, Dubravko},
  title = {A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {4},
  pages = {655},
  doi = {10.3390/rs16040655}
}
Kostenlos starten →