A5024342243- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Remote Sensing and LiDAR Applications
- Land Use and Ecosystem Services
- Water Resource Management and Quality
- Spectroscopy and Chemometric Analyses
- Hydrology and Watershed Management Studies
- Smart Agriculture and AI
- Flood Risk Assessment and Management
- Advanced Image Fusion Techniques
- Tree Root and Stability Studies
- Geochemistry and Geologic Mapping
- Fire effects on ecosystems
- Environmental and Ecological Studies
- Forest Insect Ecology and Management
- Air Quality and Health Impacts
- Forest ecology and management
- Water-Energy-Food Nexus Studies
- Robotics and Sensor-Based Localization
- Water resources management and optimization
- Hydrology and Drought Analysis
- Geological and Tectonic Studies in Latin America
- Urban Heat Island Mitigation
- Urban Green Space and Health
University of Cauca
2015-2024
Universidad Tecnológica de Bolívar
2022-2024
Pontificia Universidad Javeriana
2024
Fondazione Bruno Kessler
2014-2022
University of Technology Malaysia
2021
Water and Land Resource Centre
2021
Indian Institute of Technology Delhi
2021
Newcastle University
2021
Addis Ababa University
2021
International Water Management Institute
2021
Insect outbreaks affect forests, causing the deaths of trees and high economic loss. In this study, we explored detection European spruce bark beetle (Ips typographus, L.) at individual tree crown level using multispectral satellite images. Moreover, possibility tracking progression outbreak over time multitemporal data. Sentinel-2 data acquired during summer 2020 a beetle–infested area in Italian Alps were used for mapping time, while airborne lidar to automatically detect crowns classify...
To overcome the limited capability of most state-of-the-art change detection (CD) methods in modeling spatial context multispectral high resolution (HR) images and exploiting all spectral bands jointly, this letter presents a novel unsupervised deep-learning-based CD method that can effectively model contextual information handle large number HR images. This is achieved by after grouping them into spectral-dedicated band groups. eliminate necessity multitemporal training data, proposed...
Wind disturbances represent the main source of damage in European forests, affecting them directly (windthrows) or indirectly due to secondary damages (insect outbreaks and forest fires). The assessment windthrows is very important establish adequate management plans remote sensing can be useful for this purpose. Many types optical data are available with different spectral, spatial temporal resolutions, many options possible acquisition, i.e. immediately after event a certain time....
Abstract Over the last two decades, several data sets have been developed to assess flood risk at global scale. In recent years, some of these become detailed enough be informative national scales. The use nationally could enormous benefits in areas lacking existing information and allow better management decisions disaster response. this study, we evaluate usefulness for assessing five countries: Colombia, England, Ethiopia, India, Malaysia. National assessments are carried out each...
This paper proposes an approach for the detection of changes in multitemporal Very High Resolution (VHR) optical images acquired by different multispectral sensors. The proposed approach, which is inspired a recent framework developed to support design change-detection systems single-sensor VHR remote sensing images, addresses and integrates general strategy effectively deal with multisensor information, i.e., perform change between sensors on two dates. achieved definition procedures...
Land Use and Cover (LULC) classification using remote sensing data is a challenging problem that has evolved with the update launch of new satellites in orbit. As are launched higher spatial spectral resolution shorter revisit times, LULC to take advantage these improvements. However, advancements also bring challenges, such as need for more sophisticated algorithms process increased volume complexity data. In recent years, deep learning techniques, convolutional neural networks (CNNs), have...
Satellite image time series (SITS), such as those by Sentinel-2 (S2) satellites, provides a large amount of information due to their combined temporal, spatial, and spectral resolutions. The high revisit frequency spatial resolution S2 result in: 1) increase in the probability acquiring cloud-free images 2) availability detailed for analyzing small objects. These characteristics are interest precision agriculture, where temporally dense SITS can benefit understanding crop behaviors. In past,...
Abstract Particulate matter, PM 10 and 2 . 5 , represents common air pollutants in cities constitute a considerable threat to public health impacting daily activity of people living city. In large cities, the main sources are diesel engine exhaust, brake dust, particulate matter from vehicle tires. These particles can be deposited, filtered, considerably reduced if there is vegetative surface neighborhoods, thus eliminating part these reducing their harmful footprint. This study evaluates...
The classification of land covers is one the most relevant tasks carried on to understand state a certain region. Additional studies about biodiversity, hydrology, human impact, modeling dynamics, and phenology in study area, can be on. In these cases, wide temporal series images need considered order get tendencies throughout years. some regions, such as South-West part Colombia (Andean region), over large areas are needed obtain unified coherent statistics that representative This means...
Satellite Image Time Series (SITS), such as the ones acquired by new Sentinel-2 (S2), combine a large amount of information compared to previous satellite generations since better trade-off in terms spatial/spectral/temporal resolutions is guaranteed. The characteristics S2 SITS become more relevant agricultural analysis, where availability continuous and/or dense important map and analyze crops dynamics. So far, agriculture applications have been limited spatial temporal monthly or yearly...
The availability of multitemporal images acquired by several very high geometrical resolution (VHR) optical sensors makes it possible to build VHR image time series (TS) over the same geographical area with a temporal better than one achievable when considering single sensor. However, such TS include showing different characteristics from geometrical, radiometrical, and spectral viewpoint. Thus, there is need methods for building homogeneous using multispectral multisensor images. By...
This paper focuses on the scientific preliminary results of project "S2-4Sci Land and Water - Multitemporal Analysis" funded by European Space Agency (ESA) in framework Scientific Exploitation Operational Missions (SEOM). The aim is development advanced multitemporal methods tailored specific properties S2 images. Sentinel-2 (S2) constellation has a huge potential for analysis, due to increased geometrical resolution, novel spectral capabilities, swath width 290Km short revisit time. Three...
One of the most common approaches to unsupervised change detection (CD) in multispectral images is vector analysis (CVA). CVA computes difference image and exploits its statistical distribution (hyper-) spherical coordinates by means two steps: 1) magnitude 2) direction thresholding. The steps require assumptions on: model class distributions number changes. However, both are seldom satisfied or difficult formulate, especially when considering VHR images. Thus, we propose an approach...
Crop-type classification has been attracting a lot of attention in recent years. In particular since the launch Sentinel-2 (S2) satellite which combines large amount spectral and spatial information, compared to previous generations. literature, several methods exist that perform crop time series, but most them: i) work at pixel level; ii) single-data analysis; and/or iii) consider single feature. This results low performance state-of-the-art methods. paper presents an approach works...
Availability of multitemporal (MT) images, such as the sentinel-2 (S2) ones, offers accurate spatial, spectral and temporal information to effectively monitor vegetation, more specifically agriculture. Agricultural practices can benefit from temporally dense satellite image time series (SITS) for understanding phenological evolution behavior crops. Developing techniques that deal with high spatial correlation resolution requires a shift in processing paradigm poses new challenges terms data...
Wind represents a primary source of disturbances in forests, necessitating an assessment the resulting damage to ensure appropriate forest management. Remote sensing, encompassing both active and passive techniques, offers valuable efficient approach for this purpose, enabling coverage large areas while being cost-effective. Passive remote sensing data could be affected by presence clouds, unlike systems such as Synthetic Aperture Radar (SAR) which are relatively less affected. Therefore,...
This work aims at developing an approach to the detection of changes in multisensor multitemporal VHR optical images. The main steps proposed method are: i) data homogenization; and ii) change takes advantage of: conversion physical quantities suggested by Pacifici <i>et. al.</i><sup>1</sup> , framework for design systems images presented Bruzzone Bovolo<sup>2</sup> unsupervised Bovolo Bruzzone<sup>3</sup>. Multisensor homogenization is achieved during pre-processing taking into account...
Change Detection (CD) is an important application of remote sensing. Recent technological evolution resulted in the availability optical multispectral sensors that provide High spatial Resolution (HR) images with many spectral bands. Such characteristics allow for new applications CD, however present challenges on proper exploitation information. HR multitemporal data processing challenging due to correlation pixels and context information needs be exploited benefit from images. Moreover...
Satellite Image Time Series (SITS), such as the ones acquired by new Sentinel-2 (S2), combine a large amount of information compared to previous satellite generations since better trade-off in terms spatial/spectral/temporal resolutions is guaranteed. The specific characteristic acquiring images under overlapped orbits, offered S2, results in: i) availability irregularly sampled acquisitions and ii) increase probability acquire cloud free over time. This becomes relevant agricultural...
Norway spruce pathogenic fungi causing root, butt and stem rot represent a substantial problem for the forest sector in many countries. Early detection of presence is important efficient management resources but due to its nature, which does not generate evident exterior signs, it very difficult detect without invasive measurements. Remote sensing has been widely used monitor health status relation pathogens infestations. In particular, multi-temporal remotely sensed data have shown be...
The availability of multitemporal images acquired by several very high geometrical resolution (VHR) optical sensors makes it possible to build VHR image Time-Series (TS) with a temporal better than the one achievable when considering single sensor. However, such TS include showing different characteristics from geometrical, radiometrical and spectral viewpoint. Thus, there is need methods for building consistent using multispectral Multi-Sensor (MS) images. Here we focus on domain only,...