Geospatial-AI

Clouds usually represent a big problem for optical remote sensing. A wide range of works have been developed in producing efficient cloud detection algorithms.

Understanding the types of vegetation that composes the land cover on non-anthropic areas and the land use for anthropic areas is essential to understand ecosystems dynamic

Estimating aboveground biomass is essential for generating vegetation inventories and understanding carbon cycles.

An accurate method for automatically mapping deforested areas constitute an important tool to inform and enable deforestation containment policies.

The Brazilian cerrado biome is under pressure, as an increasing part of it is converted to agriculture.

As an essential part of food security, diet diversity often requires frequent household food security surveys to monitor.

Sufficient nutrition remains a major challenge for rural households in the Sub-saharan region of Africa.

Objective

To develop a deep learning model to estimate the timing of phenological events over large area

To develop a model to estimate the timing of phenological events over large areas from time series of earth observation data using vision transformers, a fierce alternative to tra

Global production, transportation, and consumption of oil can cause inevitable spills into the environment (typically from pipelines, oil wells, and storage facilities) cont