2022
DOI: 10.1109/mgrs.2021.3136100
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning and Earth Observation to Support the Sustainable Development Goals: Current approaches, open challenges, and future opportunities

Abstract: This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
20
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 75 publications
(20 citation statements)
references
References 255 publications
0
20
0
Order By: Relevance
“…Models based on these optical satellite image time-series (SITS) can explain and predict the states and trends of our environment. They are essential to understand the challenges related to climate change [2]. Since their launch in 2015 and 2017, SITS from the twin Sentinel-2 satellites have already shown a clear benefit in biodiversity monitoring [3], [4], forest mapping [5], [6], water quality [7], [8], agricultural monitoring [9], [10] or disaster management [11], [12].…”
Section: Introductionmentioning
confidence: 99%
“…Models based on these optical satellite image time-series (SITS) can explain and predict the states and trends of our environment. They are essential to understand the challenges related to climate change [2]. Since their launch in 2015 and 2017, SITS from the twin Sentinel-2 satellites have already shown a clear benefit in biodiversity monitoring [3], [4], forest mapping [5], [6], water quality [7], [8], agricultural monitoring [9], [10] or disaster management [11], [12].…”
Section: Introductionmentioning
confidence: 99%
“…On the other hand, SAR sensors provide high resolution and weather independent data but do not provide readily interpretable images. As both have their benefits, several research efforts have shown the possibility of combining the data from these two sensors to obtain better quality information [1]. Learning features from both modalities has also shown significant advantages in previous works [2]- [4].…”
Section: Introductionmentioning
confidence: 99%
“…These two models are chosen due to the fact that they are standard and widely-adopted methodologies for land cover mapping from satellite image time series data. More in detail, the former has an established popularity in the remote sensing community due to the accuracy of its classifications [56] while the latter approach is representative of the recent deep learning methods that explicitly manage the temporal dimension that heavily characterizes SITS data [57].…”
Section: • the Conditional Adversarial Domain Adaptation Withmentioning
confidence: 99%