Advances in Remote Sensing for Global Forest Monitoring

• Autore: Tomppo Erkki
• Pubblicazione: Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021
• Descrizione fisica: 1 online resource (352 p.)
• Soggetto topico: Environmental economics; Research and information: general
• Soggetto non controllato: activity data; bootstrapping; boreal forest; Bowen ratio; C-band; canopy height model; carbon flux; classification; compatible equation; constrained neighbor interpolation; CRFasRNN; CUSUM; data assessment; data fusion; deep learning; deforestation; degradation; digital surface model; digital terrain model; drought; dual-FCN8s; EBLUP; emissions factor; error propagation; error-in-variable modeling; FCN8s; field measured LAI; forest area change; forest cover; forest disturbance mapping; forest monitoring; forest structure change; forest type; genetic algorithm; Germany; GF2; improved k-NN; inconsistency; IPCC good practice guidelines; La Rioja; land use land cover; Landsat; leave-one-out cross-validation; LiDAR; logistic regression; machine-learning; magnitude; multinomial logistic regression; multitemporal LiDAR and stand-level estimates; n/a; near real-time monitoring; nonlinear seemingly unrelated regression; NRT monitoring; ordinary neighbor interpolation; Picea crassifolia Kom; point cloud density; random forest; random forests; remotely sensed LAI; removals factor; savanna; Sentinel 2; Sentinel-1; Sentinel-2; small area estimation; South Africa; state space models; statistical estimator; stereo imagery; support vector machine; synthetic aperture radar; temperate forest; temporal dynamics; time series satellite data; tropical forest; tropical peat; uncertainty; uncertainty evaluation; validation; windstorm damage
• Persona (resp. second.): PraksJaan; WangGuangxing; WaserLars T; TomppoErkki
• Sommario/riassunto: The topics of the book cover forest parameter estimation, methods to assess land cover and change, forest disturbances and degradation, and forest soil drought estimations. Airborne laser scanner data, aerial images, as well as data from passive and active sensors of different spatial, spectral and temporal resolutions have been utilized. Parametric and non-parametric methods including machine and deep learning methods have been employed. Uncertainty estimation is a key topic in each study. In total, 15 articles are included, of which one is a review article dealing with methods employed in remote sensing aided greenhouse gas inventories, and one is the Editorial summary presenting a short review of each article.
• Titolo autorizzato: Advances in Remote Sensing for Global Forest Monitoring
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910557338103321
• Lo trovi qui: Univ. Federico II