FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3086184474> ?p ?o ?g. }

• W3086184474 endingPage "2957" @default.
• W3086184474 startingPage "2957" @default.
• W3086184474 abstract "High resolution satellite imagery and modern machine learning methods hold the potential to fill existing data gaps in where crops are grown around the world at a sub-field level. However, high resolution crop type maps have remained challenging to create in developing regions due to a lack of ground truth labels for model development. In this work, we explore the use of crowdsourced data, Sentinel-2 and DigitalGlobe imagery, and convolutional neural networks (CNNs) for crop type mapping in India. Plantix, a free app that uses image recognition to help farmers diagnose crop diseases, logged 9 million geolocated photos from 2017–2019 in India, 2 million of which are in the states of Andhra Pradesh and Telangana in India. Crop type labels based on farmer-submitted images were added by domain experts and deep CNNs. The resulting dataset of crop type at coordinates is high in volume, but also high in noise due to location inaccuracies, submissions from out-of-field, and labeling errors. We employed a number of steps to clean the dataset, which included training a CNN on very high resolution DigitalGlobe imagery to filter for points that are within a crop field. With this cleaned dataset, we extracted Sentinel time series at each point and trained another CNN to predict the crop type at each pixel. When evaluated on the highest quality subset of crowdsourced data, the CNN distinguishes rice, cotton, and “other” crops with 74% accuracy in a 3-way classification and outperforms a random forest trained on harmonic regression features. Furthermore, model performance remains stable when low quality points are introduced into the training set. Our results illustrate the potential of non-traditional, high-volume/high-noise datasets for crop type mapping, some improvements that neural networks can achieve over random forests, and the robustness of such methods against moderate levels of training set noise. Lastly, we caution that obstacles like the lack of good Sentinel-2 cloud mask, imperfect mobile device location accuracy, and preservation of privacy while improving data access will need to be addressed before crowdsourcing can widely and reliably be used to map crops in smallholder systems." @default.
• W3086184474 created "2020-09-21" @default.
• W3086184474 creator A5005559785 @default.
• W3086184474 creator A5016903297 @default.
• W3086184474 creator A5022629991 @default.
• W3086184474 creator A5026642372 @default.
• W3086184474 creator A5063256172 @default.
• W3086184474 creator A5088223699 @default.
• W3086184474 creator A5088966490 @default.
• W3086184474 date "2020-09-11" @default.
• W3086184474 modified "2023-10-06" @default.
• W3086184474 title "Mapping Crop Types in Southeast India with Smartphone Crowdsourcing and Deep Learning" @default.
• W3086184474 cites W1514928307 @default.
• W3086184474 cites W1990653740 @default.
• W3086184474 cites W2018400577 @default.
• W3086184474 cites W2032109992 @default.
• W3086184474 cites W2033309242 @default.
• W3086184474 cites W2057641906 @default.
• W3086184474 cites W2075271931 @default.
• W3086184474 cites W2076473735 @default.
• W3086184474 cites W2077094975 @default.
• W3086184474 cites W2077109367 @default.
• W3086184474 cites W2108806738 @default.
• W3086184474 cites W2109006150 @default.
• W3086184474 cites W2118037698 @default.
• W3086184474 cites W2133941557 @default.
• W3086184474 cites W2138751033 @default.
• W3086184474 cites W2155939589 @default.
• W3086184474 cites W2167594433 @default.
• W3086184474 cites W2173499079 @default.
• W3086184474 cites W2248723555 @default.
• W3086184474 cites W2262752710 @default.
• W3086184474 cites W2273708466 @default.
• W3086184474 cites W2307094448 @default.
• W3086184474 cites W2328362812 @default.
• W3086184474 cites W2331071973 @default.
• W3086184474 cites W2347192404 @default.
• W3086184474 cites W2418853085 @default.
• W3086184474 cites W2532003389 @default.
• W3086184474 cites W2534397573 @default.
• W3086184474 cites W2558892021 @default.
• W3086184474 cites W2562837240 @default.
• W3086184474 cites W2588316148 @default.
• W3086184474 cites W2594060544 @default.
• W3086184474 cites W2621021710 @default.
• W3086184474 cites W2725897987 @default.
• W3086184474 cites W2745131289 @default.
• W3086184474 cites W2750585339 @default.
• W3086184474 cites W2782220608 @default.
• W3086184474 cites W2803901105 @default.
• W3086184474 cites W2804839269 @default.
• W3086184474 cites W2890098102 @default.
• W3086184474 cites W2892045252 @default.
• W3086184474 cites W2905254777 @default.
• W3086184474 cites W2909728654 @default.
• W3086184474 cites W2911964244 @default.
• W3086184474 cites W2919115771 @default.
• W3086184474 cites W2921950230 @default.
• W3086184474 cites W2939118835 @default.
• W3086184474 cites W2943472941 @default.
• W3086184474 cites W2944643337 @default.
• W3086184474 cites W2959328963 @default.
• W3086184474 cites W2964010366 @default.
• W3086184474 cites W3018762055 @default.
• W3086184474 cites W3104839310 @default.
• W3086184474 doi "https://doi.org/10.3390/rs12182957" @default.
• W3086184474 hasPublicationYear "2020" @default.
• W3086184474 type Work @default.
• W3086184474 sameAs 3086184474 @default.
• W3086184474 citedByCount "44" @default.
• W3086184474 countsByYear W30861844742020 @default.
• W3086184474 countsByYear W30861844742021 @default.
• W3086184474 countsByYear W30861844742022 @default.
• W3086184474 countsByYear W30861844742023 @default.
• W3086184474 crossrefType "journal-article" @default.
• W3086184474 hasAuthorship W3086184474A5005559785 @default.
• W3086184474 hasAuthorship W3086184474A5016903297 @default.
• W3086184474 hasAuthorship W3086184474A5022629991 @default.
• W3086184474 hasAuthorship W3086184474A5026642372 @default.
• W3086184474 hasAuthorship W3086184474A5063256172 @default.
• W3086184474 hasAuthorship W3086184474A5088223699 @default.
• W3086184474 hasAuthorship W3086184474A5088966490 @default.
• W3086184474 hasBestOaLocation W30861844741 @default.
• W3086184474 hasConcept C108583219 @default.
• W3086184474 hasConcept C119857082 @default.
• W3086184474 hasConcept C136764020 @default.
• W3086184474 hasConcept C137580998 @default.
• W3086184474 hasConcept C146849305 @default.
• W3086184474 hasConcept C153180895 @default.
• W3086184474 hasConcept C154945302 @default.
• W3086184474 hasConcept C169258074 @default.
• W3086184474 hasConcept C205649164 @default.
• W3086184474 hasConcept C41008148 @default.
• W3086184474 hasConcept C62230096 @default.
• W3086184474 hasConcept C62649853 @default.
• W3086184474 hasConcept C81363708 @default.
• W3086184474 hasConcept C97137747 @default.
• W3086184474 hasConceptScore W3086184474C108583219 @default.

• next