Version 1
: Received: 1 August 2022 / Approved: 4 August 2022 / Online: 4 August 2022 (16:18:26 CEST)
How to cite:
Dan, T.-T.; Frank, Y. G.; Chamaka, K.; Kavinda, G.; Sangita, D.; Anthony, B. D.; Manzul, H. K. Collecting and Disseminating Ground Truth Data for Generation of Agriculture Statistics. Preprints2022, 2022080112. https://doi.org/10.20944/preprints202208.0112.v1
Dan, T.-T.; Frank, Y. G.; Chamaka, K.; Kavinda, G.; Sangita, D.; Anthony, B. D.; Manzul, H. K. Collecting and Disseminating Ground Truth Data for Generation of Agriculture Statistics. Preprints 2022, 2022080112. https://doi.org/10.20944/preprints202208.0112.v1
Dan, T.-T.; Frank, Y. G.; Chamaka, K.; Kavinda, G.; Sangita, D.; Anthony, B. D.; Manzul, H. K. Collecting and Disseminating Ground Truth Data for Generation of Agriculture Statistics. Preprints2022, 2022080112. https://doi.org/10.20944/preprints202208.0112.v1
APA Style
Dan, T. T., Frank, Y. G., Chamaka, K., Kavinda, G., Sangita, D., Anthony, B. D., & Manzul, H. K. (2022). Collecting and Disseminating Ground Truth Data for Generation of Agriculture Statistics. Preprints. https://doi.org/10.20944/preprints202208.0112.v1
Chicago/Turabian Style
Dan, T., Burgard Dean Anthony and Hazarika Kumar Manzul. 2022 "Collecting and Disseminating Ground Truth Data for Generation of Agriculture Statistics" Preprints. https://doi.org/10.20944/preprints202208.0112.v1
Abstract
Over the last few years, Earth Observation (EO) data has shifted towards increased use to produce official statistics, particularly in the agriculture sector. National statistics offices worldwide, including in Asia and the Pacific, are expanding their use of EO data to produce agricultural statistics such as crop classification, yield estimation, irrigation mapping, and crop loss estimation. The advances in image classification, such as pixel-based and phenology-based classifications, and machine learning create new opportunities for researchers to analyze EO data applied to agriculture statistics. However, it requires the ground truth (GT) data because classification result mainly depends on the quality of GT. Therefore, in this study, we introduced a random sampling approach to design and collect GT data using EO imagery and ancillary data. As a result of data collection, GT data improve the algorithms and validates classification results. Nevertheless, despite the importance of GT data, they are rarely disseminated as a data product in themselves. Thus, this results in an untapped opportunity to share GT data as a global public good, and improved use of survey and census data as a source of GT data.
Keywords
ground truth data; drone; mobile application; windshield survey; sample design; crop mapping; agriculture statistics; data dissemination; earth observation data; spatial database.
Subject
Biology and Life Sciences, Agricultural Science and Agronomy
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
,
,
,
