FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209804565> ?p ?o ?g. }

• W3209804565 endingPage "10963" @default.
• W3209804565 startingPage "10953" @default.
• W3209804565 abstract "Forest canopy cover (FCC) plays an important role in many ecological, hydrological and forestry applications. For large-scale applications, FCC is usually estimated from remotely sensed data by inverting radiative transfer models (RTMs) or using data-driven regressions. In this study, we proposed a hybrid model, which combines 3D RTMs and transfer learning-based convolutional neural network (T-CNN), to estimate FCC from very high-resolution satellite images (e.g., Chinese GaoFen-2, 1 m resolution with 4 bands). Unlike common hybrid models that are purely trained with simulation data, T-CNN combines simulation data-based pre-training and actual data-based transfer learning, which is a widely used technique in artificial intelligence for fine-tuning models. The performance of T-CNN was compared with a random forest (RF) model and two general CNN models, including CNN trained with actual dataset only (Data-CNN) and CNN trained with RTM simulation data only (RTM-CNN). Results on the independent validation dataset (not used in training stage) showed that T-CNN had higher accuracy (RMSE = 0.121, R2 = 0.83), compared with RF (RMSE = 0.26, R2 = 0.61), Data-CNN (RMSE = 0.142, R2 = 0.81), and RTM-CNN (RMSE = 0.144, R2 = 0.73), which indicates that T-CNN has a strong transferability. Tests on different training sizes showed that T-CNN (0.084<RMSE<0.108) provided constantly better performances than RF (0.116<RMSE<0.122) and Data-CNN (0.103<RMSE<0.128), which demonstrates the potential of T-CNN as an alternative to RTM-based inversion and data-driven regressions to estimate FCC, especially when training data is imbalanced and inadequate." @default.
• W3209804565 created "2021-11-08" @default.
• W3209804565 creator A5022044383 @default.
• W3209804565 creator A5051021577 @default.
• W3209804565 creator A5069389278 @default.
• W3209804565 creator A5076965773 @default.
• W3209804565 date "2021-01-01" @default.
• W3209804565 modified "2023-09-23" @default.
• W3209804565 title "Combining 3D Radiative Transfer Model and Convolutional Neural Network to Accurately Estimate Forest Canopy Cover From Very High-Resolution Satellite Images" @default.
• W3209804565 cites W1819217904 @default.
• W3209804565 cites W1827322724 @default.
• W3209804565 cites W1948133483 @default.
• W3209804565 cites W1964789567 @default.
• W3209804565 cites W1968019505 @default.
• W3209804565 cites W1998979050 @default.
• W3209804565 cites W2012409721 @default.
• W3209804565 cites W2017730203 @default.
• W3209804565 cites W2018248490 @default.
• W3209804565 cites W2026470773 @default.
• W3209804565 cites W2029082275 @default.
• W3209804565 cites W2031925862 @default.
• W3209804565 cites W2039393019 @default.
• W3209804565 cites W2041122228 @default.
• W3209804565 cites W2053886687 @default.
• W3209804565 cites W2061918237 @default.
• W3209804565 cites W2063545567 @default.
• W3209804565 cites W2063907334 @default.
• W3209804565 cites W2069358120 @default.
• W3209804565 cites W2073100112 @default.
• W3209804565 cites W2078619499 @default.
• W3209804565 cites W2078665635 @default.
• W3209804565 cites W2086783159 @default.
• W3209804565 cites W2098823605 @default.
• W3209804565 cites W2105307752 @default.
• W3209804565 cites W2110850123 @default.
• W3209804565 cites W2133237420 @default.
• W3209804565 cites W2141444291 @default.
• W3209804565 cites W2146205032 @default.
• W3209804565 cites W2157144502 @default.
• W3209804565 cites W2165608115 @default.
• W3209804565 cites W2165698076 @default.
• W3209804565 cites W2166312616 @default.
• W3209804565 cites W2218047931 @default.
• W3209804565 cites W2266591399 @default.
• W3209804565 cites W2285717070 @default.
• W3209804565 cites W2313448762 @default.
• W3209804565 cites W2436494909 @default.
• W3209804565 cites W2531185277 @default.
• W3209804565 cites W2541708856 @default.
• W3209804565 cites W2588987202 @default.
• W3209804565 cites W2626736357 @default.
• W3209804565 cites W2790979755 @default.
• W3209804565 cites W2809537360 @default.
• W3209804565 cites W2888248463 @default.
• W3209804565 cites W2888424087 @default.
• W3209804565 cites W2897870114 @default.
• W3209804565 cites W2899101283 @default.
• W3209804565 cites W2905511257 @default.
• W3209804565 cites W2911964244 @default.
• W3209804565 cites W2913323966 @default.
• W3209804565 cites W2968347155 @default.
• W3209804565 cites W2973244992 @default.
• W3209804565 cites W2981914352 @default.
• W3209804565 cites W2987752547 @default.
• W3209804565 cites W2995363336 @default.
• W3209804565 cites W3000544281 @default.
• W3209804565 cites W3005101149 @default.
• W3209804565 cites W3007497172 @default.
• W3209804565 cites W3008439211 @default.
• W3209804565 cites W3085968088 @default.
• W3209804565 cites W3088507381 @default.
• W3209804565 cites W3124539583 @default.
• W3209804565 cites W3125880037 @default.
• W3209804565 cites W3130951558 @default.
• W3209804565 cites W3153113051 @default.
• W3209804565 cites W61452412 @default.
• W3209804565 doi "https://doi.org/10.1109/jstars.2021.3122509" @default.
• W3209804565 hasPublicationYear "2021" @default.
• W3209804565 type Work @default.
• W3209804565 sameAs 3209804565 @default.
• W3209804565 citedByCount "4" @default.
• W3209804565 countsByYear W32098045652022 @default.
• W3209804565 countsByYear W32098045652023 @default.
• W3209804565 crossrefType "journal-article" @default.
• W3209804565 hasAuthorship W3209804565A5022044383 @default.
• W3209804565 hasAuthorship W3209804565A5051021577 @default.
• W3209804565 hasAuthorship W3209804565A5069389278 @default.
• W3209804565 hasAuthorship W3209804565A5076965773 @default.
• W3209804565 hasBestOaLocation W32098045651 @default.
• W3209804565 hasConcept C105795698 @default.
• W3209804565 hasConcept C108583219 @default.
• W3209804565 hasConcept C121332964 @default.
• W3209804565 hasConcept C127413603 @default.
• W3209804565 hasConcept C139945424 @default.
• W3209804565 hasConcept C146978453 @default.
• W3209804565 hasConcept C150899416 @default.
• W3209804565 hasConcept C153180895 @default.
• W3209804565 hasConcept C154945302 @default.

• next