An NDVI-data harmonic analysis to study deforestation in Peru’s Tahuamanu province during 2001–2011

Peña, Marco A.; Navarro, F. A. R.

doi:10.1080/01431161.2015.1136446

Cited by 7 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…La deforestación es una de las principales causas de erosión y puede ser detectada a partir de imágenes de satélite mediante señales abruptas que refleja cambios en la cubierta vegetal (Finer et al 2018). Tradicionalmente, para ello se han usado índices espectrales y series temporales (Eckert et al 2015;Muñoz-Peña et al 2016). Los nuevos métodos basados en aprendizaje profundo permiten elaborar mapas cada vez más precisos de zonas deforestadas (Mhatre et al 2019: Maretto et al 2020Ortega et al 2020;Lee et al 2020).…”

Section: Variables Biofísicas En El Estudio De La Desertificaciónunclassified

Potential of artificial intelligence to advance the study of desertification

Guirado

Martínez‐Valderrama

2021

ECOS

View full text Add to dashboard Cite

La desertificación es un problema global que afecta a más de 1.500 millones de personas que viven en los lugares más pobres y vulnerables del planeta. En los últimos años numerosos estudios han contribuido a aportar información para evaluar el problema. Algunos de ellos se basan en analizar variables biofísicas y socio-económicas mediante técnicas de inteligencia artificial. Por ejemplo, se han usado para completar datos de anomalías en la estimación de almacenamiento de agua, la identificación precisa de cobertura del suelo, estimación de la radiación solar diaria a nivel global y mejora en predicciones climáticas, entre otras. Si bien su uso todavía no está muy extendido, el futuro en los estudios sobre desertificación parece prometedor. En este trabajo revisamos el potencial de las técnicas de inteligencia artificial (aprendizaje automático y aprendizaje profundo) en el estudio de la desertificación y su reciente crecimiento en los últimos años. Durante el periodo 2015-2020 el número de publicaciones que implementan el aprendizaje profundo se incrementó un 63%, mientras que para el aprendizaje automático su crecimiento fue más modesto, del 3%. En particular, cuando buscamos estudios relacionados con la desertificación, las cifras de crecimiento son más llamativas: un incremento medio del 103% en estudios con aprendizaje profundo, y del 43% en aprendizaje automático. Sin embargo, se requieren más estudios y esfuerzos que agrupen todas las disciplinas implicadas en el estudio de la desertificación para obtener una visión global y transversal de este fenómeno y así diseñar acciones efectivas para mitigar sus efectos adversos o anticiparse a ellos.

show abstract

Section: Variables Biofísicas En El Estudio De La Desertificaciónunclassified

Potential of artificial intelligence to advance the study of desertification

Guirado

Martínez‐Valderrama

2021

ECOS

View full text Add to dashboard Cite

show abstract

“…used in urban planning [1], [2], disaster assessment [3], forest monitoring [4], [5], and environmental monitoring [6].…”

mentioning

confidence: 99%

Adaptive Spatial and Difference Learning for Change Detection

Liu

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Change detection refers to revealing the surface changes from multitemporal images of a given scene, where changed regions of different size and shape may appear anywhere. Convolutional neural network, as one of the most widely used deep learning architectures, has shown good performance in change detection task recently. However, due to multiple convolution and pooling operators in deep architectures, it often happens that small changes are missed and sharp edges are blurred. In this article, an adaptive spatial and difference learning method is proposed to tackle this problem, which mainly contains a feature-adapted difference learning (FADL) module and a difference recalibration (DR) module. In FADL, a kernel-adapted spatial learning part is constructed to capture varying spatial information, which selects proper kernels to adapt different shape and size of changed regions; a joint feature refinement part is employed to learn comprehensive features between bitemporal data, which are further enhanced by difference information. In addition, DR with shallow features is designed to recalibrate spatial and difference details further. From the experiments on three public datasets, our proposed method can relieve the spatial ambiguity problem and obtains the optimal results among the compared change detection methods.

show abstract

Estimating fractional cover of plant functional types in African savannah from harmonic analysis of MODIS time-series data

Ibrahim

Balzter

Tansey

et al. 2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

Assessments of tree/grass fractional cover in savannahs using remote sensing are challenging due to the heterogeneous mixture of the two plant functional types. Time-series decomposition models can be used to characterize vegetation phenology from satellite data, but have rarely been used for attributing phenological signal components to different plant functional types. Here, tree/ grass dynamics are assessed in savannah ecosystems using timeseries decomposition of 14 years of Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index data acquired from 2002 to 2015. The decomposition method uses harmonic analysis and tests the individual harmonic terms for statistical significance. Field data of fractional cover of trees and grasses were collected for 28 plots in Kruger National Park, South Africa. Matching MODIS pixels were analysed for their tree/grass phenological signals. Tree/grass annual and interannual variability were then assessed based on the harmonic models. In most harmonic cycles, grass-dominated sites had higher amplitudes than tree-dominated sites, while the tree green-up started earlier than grasses, before the start of the wet season. While changes in tree phenology are gradual, grasses present higher variability over time. Tree cover showed a significant correlation with the amplitude (r (correlation coefficient) = −0.59, p = 0.001) and phase of the first harmonic term (r = −0.73, p = 0.0001) and the number of cycles of the second harmonic term (r = 0. 56, p = 0.002). Grass cover was also significantly correlated with the amplitude (r = 0. 51, p = 0.005) and phase of the first harmonic term (r = 0.55, p = 0.002) and the number of cycles of the second harmonic term (r = −0.52, p = 0.005). The positive correlation of grass cover with phase and negative correlation with number of cycles is indicating a late greening period and higher variability, respectively. Tree cover estimated from the phase of the strongest harmonic term showed a positive correlation with field-measured tree cover (R 2 (coefficient of determination) = 0.55, p < 0.01, slope = 0.93, root mean square error = 13.26%). The estimated tree cover also had a strong correlation with the woody cover map (r = 0.78, p < 0.01) produced by Bucini. The results show that MODIS time-series data can be used to estimate the fractional tree cover in heterogeneous savannahs from the phase of the plant functional type's phenological behaviour. This study shows that harmonic analysis is able to discriminate between fractional cover by trees and grasses in savannahs. The quantitative analysis of tree/grass phenology from satellite time-series data enables a better understanding of the dynamics of the tree/grass competition and coexistence.

show abstract

An NDVI-data harmonic analysis to study deforestation in Peru’s Tahuamanu province during 2001–2011

Cited by 7 publications

References 22 publications

Potential of artificial intelligence to advance the study of desertification

Potential of artificial intelligence to advance the study of desertification

Adaptive Spatial and Difference Learning for Change Detection

Estimating fractional cover of plant functional types in African savannah from harmonic analysis of MODIS time-series data

Contact Info

Product

Resources

About