arXiv subjects

Miguel Pereira

Publications and source records attributed to Miguel Pereira.

4 recordsLinked to original sources

arXiv2026

A Remote Approach to Cashew Orchard Detection: Leveraging Active Learning with Satellite Imagery in Guinea-Bissau

Cashew production is a widespread economic activity in Guinea-Bissau, as well as other countries in West Africa. However, unregulated cashew production can be directly associated with increasing regionwide deforestation rates, biodiversity losses, and a fragile economic structure. There is no nationwide database for listing or georeferencing cashew orchards, so there is a clear need to remotely map their locations. In recent years, multiple methods for detecting orchards have been developed, though they have only been applied on a regional level. This work expands regional analyses to a nationwide scale. It develops a scalable and cost-effective remote approach, based on Sentinel-2 satellite imagery, using Machine Learning techniques to detect cashew orchards automatically. Margin-based Active Learning techniques were employed to develop an optimal training set in terms of the number of points and their informativeness, leading to a cashew map with 94.0% balanced accuracy obtained entirely off-site. We created two datasets and a 2021 cashew map with 10m spatial resolution that are openly accessible through GitHub. The results demonstrate the possibility of a broader cashew orchard mapping, creating a new stepping stone for this environmental application.

cs.CV↗

arXiv2024

On the Lagrangian capacity of convex or concave toric domains

We establish computational results concerning the Lagrangian capacity, originally defined by Cieliebak-Mohnke. More precisely, we show that the Lagrangian capacity of a 4-dimensional convex toric domain is equal to its diagonal. Working under the assumption that there is a suitable virtual perturbation scheme which defines the curve counts of linearized contact homology, we extend the previous result to any convex or concave toric domain. This result gives a positive answer to a conjecture of Cieliebak-Mohnke for the Lagrangian capacity of the ellipsoid.

math.SG↗

arXiv2022

Cube normalized symplectic capacities

We introduce a new normalization condition for symplectic capacities, which we call cube normalization. This condition is satisfied by the Lagrangian capacity and the cube capacity. Our main result is an analogue of the strong Viterbo conjecture for monotone toric domains in all dimensions. Moreover, we give a family of examples where standard normalized capacities coincide but not cube normalized ones. Along the way, we give an explicit formula for the Lagrangian capacity on a large class of toric domains.

math.SG↗

arXiv2022

Equivariant symplectic homology, linearized contact homology and the Lagrangian capacity

We establish computational results concerning the Lagrangian capacity from "Cieliebak and Mohnke - Punctured holomorphic curves and Lagrangian embeddings". More precisely, we show that the Lagrangian capacity of a 4-dimensional convex toric domain is equal to its diagonal. The proof involves comparisons between the Lagrangian capacity, the McDuff-Siegel capacities from "McDuff and Siegel - Symplectic capacities, unperturbed curves, and convex toric domains", and the Gutt-Hutchings capacities from "Gutt and Hutchings - Symplectic capacities from positive S1-equivariant symplectic homology". Working under the assumption that there is a suitable virtual perturbation scheme which defines the curve counts of linearized contact homology, we extend the previous result to toric domains which are convex or concave and of any dimension. For this, we use the higher symplectic capacities from "Siegel - Higher symplectic capacities". The key step is showing that moduli spaces of asymptotically cylindrical holomorphic curves in ellipsoids are transversely cut out.

math.SG↗