Challenges and progress in applying space technology in support of the sustainable development goals

D Wood, M Rathnasabapathy, KJ Stober, P Menon - Acta Astronautica, 2024 - Elsevier
The global community, with coordination from the United Nations, is energized to pursue the
Sustainable Development Goals (SDGs), a list of 17 important aspirations that summarize …

Lightweight, pre-trained transformers for remote sensing timeseries

G Tseng, R Cartuyvels, I Zvonkov, M Purohit… - arXiv preprint arXiv …, 2023 - arxiv.org
Machine learning methods for satellite data have a range of societally relevant applications,
but labels used to train models can be difficult or impossible to acquire. Self-supervision is a …

How accurate are existing land cover maps for agriculture in Sub-Saharan Africa?

H Kerner, C Nakalembe, A Yang, I Zvonkov… - Scientific Data, 2024 - nature.com
Satellite Earth observations (EO) can provide affordable and timely information for assessing
crop conditions and food production. Such monitoring systems are essential in Africa, where …

Mission Critical--Satellite Data is a Distinct Modality in Machine Learning

E Rolf, K Klemmer, C Robinson, H Kerner - arXiv preprint arXiv …, 2024 - arxiv.org
Satellite data has the potential to inspire a seismic shift for machine learning--one in which
we rethink existing practices designed for traditional data modalities. As machine learning …

[HTML][HTML] Taking it further: Leveraging pseudo-labels for field delineation across label-scarce smallholder regions

P Rufin, S Wang, SN Lisboa, J Hemmerling… - International Journal of …, 2024 - Elsevier
Satellite-based field delineation has entered a quasi-operational stage due to recent
advances in machine learning for computer vision. Transfer learning allows for the resource …

Adopting yield-improving practices to meet maize demand in Sub-Saharan Africa without cropland expansion

F Aramburu-Merlos, FAM Tenorio… - Nature …, 2024 - nature.com
Abstract Maize demand in Sub-Saharan Africa is expected to increase 2.3 times during the
next 30 years driven by demographic and dietary changes. Over the past two decades, the …

Reflections from the Workshop on AI-Assisted Decision Making for Conservation

L Xu, E Rolf, S Beery, JR Bennett, T Berger-Wolf… - arXiv preprint arXiv …, 2023 - arxiv.org
In this white paper, we synthesize key points made during presentations and discussions
from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for …

USat: A unified self-supervised encoder for multi-sensor satellite imagery

J Irvin, L Tao, J Zhou, Y Ma, L Nashold, B Liu… - arXiv preprint arXiv …, 2023 - arxiv.org
Large, self-supervised vision models have led to substantial advancements for automatically
interpreting natural images. Recent works have begun tailoring these methods to remote …

New Functionalities and Regional/National Use Cases of the Anomaly Hotspots of Agricultural Production (ASAP) Platform

F Rembold, M Meroni, V Otieno, O Kipkogei, K Mwangi… - Remote Sensing, 2023 - mdpi.com
The Anomaly hotSpots of Agricultural Production (ASAP) Decision Support System was
launched operationally in 2017 for providing timely early warning information on agricultural …

[HTML][HTML] Can we estimate farm size from field size? An empirical investigation of the field size to farm size relationship

C Jänicke, M Wesemeyer, C Chiarella, T Lakes… - Agricultural …, 2024 - Elsevier
CONTEXT Farm size is a key indicator associated with environmental, economic, and social
contexts and outcomes of agriculture. Farm size data is typically obtained from agricultural …