1
|
Jeong S, Ko J, Yeom JM. Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea. THE SCIENCE OF THE TOTAL ENVIRONMENT 2022; 802:149726. [PMID: 34464811 DOI: 10.1016/j.scitotenv.2021.149726] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/15/2021] [Revised: 08/11/2021] [Accepted: 08/13/2021] [Indexed: 06/13/2023]
Abstract
Prediction of rice yields at pixel scale rather than county scale can benefit crop management and scientific understanding because it is useful for monitoring how crop yields respond to various agricultural systems and environmental factors. In this study, we propose a methodology for the early prediction of rice yield at pixel scale combining a crop model and a deep learning model for different agricultural systems throughout South and North Korea. Initially, satellite-integrated crop models were applied to obtain a pixel-scale reference rice yield. Then, the pixel-scale reference rice yields were used as target labels in the deep learning model to leverage the advantages of crop models. Models of five different deep learning network architectures were employed to help determine the hybrid structure of long-short term memory (LSTM) and one-dimensional convolutional neural network (1D-CNN) layers by predicting the optimal model about two months ahead of harvest time. The suggested model showed good performance [R2 = 0.859, Nash-Sutcliffe model efficiency = 0.858, root mean squared error = 0.605 Mg ha-1], with specific spatial patterns of rice yields for South and North Korea. Analysis of the relative importance of the input variables showed the water-related index and maximum temperature in North Korea and the vegetation indices and geographic variables in South Korea to be crucial for predicting rice yields. The proposed approach successfully predicted and diagnosed rice yield at the pixel scale for inaccessible locations where reliable ground measurements are not available, especially North Korea.
Collapse
Affiliation(s)
- Seungtaek Jeong
- Satellite Application Division, Korea Aerospace Research Institute, 169-84 Gwahak-ro, Yuseong-gu, Daejeon 34133, Republic of Korea
| | - Jonghan Ko
- Applied Plant Science, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
| | - Jong-Min Yeom
- Satellite Application Division, Korea Aerospace Research Institute, 169-84 Gwahak-ro, Yuseong-gu, Daejeon 34133, Republic of Korea.
| |
Collapse
|
2
|
Turcotte A, Kermany N, Foster S, Proctor CA, Gilmour SM, Doria M, Sebes J, Whitton J, Cooke SJ, Bennett JR. Fixing the Canadian Species at Risk Act: identifying major issues and recommendations for increasing accountability and efficiency. Facets (Ott) 2021. [DOI: 10.1139/facets-2020-0064] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
Since the implementation of the Canadian Species at Risk Act (SARA) in 2003, deficiencies in SARA and its application have become clear. Legislative and policy inconsistencies among responsible federal agencies and the use of a subjective approach for prioritizing species protection lead to taxonomic biases in protection. Variations in legislation among provinces/territories and the reluctance of the federal government to take actions make SARA’s application often inefficient on nonfederally managed lands. Ambiguous key terms (e.g., critical habitat) and disregard for legislated deadlines in many steps impede the efficacy of SARA. Additionally, the failure to fully recognize Indigenous knowledge and to seek Indigenous cooperation in the species protection process leads to weaker government accountability, promotes inequity, and leads to missed opportunities for partnerships. New legislative amendments with well-defined and standardized steps, including an automatic listing process, a systematic prioritization program, and clearer demands (e.g., mandatory threshold to trigger safety net/emergency order) would improve the success of species at risk protection. Moreover, a more inclusive approach that brings Indigenous representatives and independent scientists together is necessary for improving SARA’s effectiveness. These changes have the potential to transform SARA into a more powerful act towards protecting Canada’s at-risk wildlife. (The graphical abstract follows.)
Collapse
Affiliation(s)
- Audrey Turcotte
- Department of Biology, University of Ottawa, 30 Marie Curie Private, Ottawa, ON K1N 6N5, Canada
| | - Natalie Kermany
- Department of Biology, University of Ottawa, 30 Marie Curie Private, Ottawa, ON K1N 6N5, Canada
| | - Sharla Foster
- Department of Biology, University of Ottawa, 30 Marie Curie Private, Ottawa, ON K1N 6N5, Canada
| | - Caitlyn A. Proctor
- Department of Biology, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
| | - Sydney M. Gilmour
- Department of Biology, University of Ottawa, 30 Marie Curie Private, Ottawa, ON K1N 6N5, Canada
| | - Maria Doria
- Department of Biology, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
| | - James Sebes
- Department of Biology, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
| | - Jeannette Whitton
- Department of Botany, University of British Columbia, 6270 University Boulevard, Vancouver, BC V6T 1Z4, Canada
| | - Steven J. Cooke
- Department of Biology, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
- Institute of Environmental and Interdisciplinary Science, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
| | - Joseph R. Bennett
- Department of Biology, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
- Institute of Environmental and Interdisciplinary Science, Carleton University, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, Canada
| |
Collapse
|
4
|
Thessen AE, Bunker DE, Buttigieg PL, Cooper LD, Dahdul WM, Domisch S, Franz NM, Jaiswal P, Lawrence-Dill CJ, Midford PE, Mungall CJ, Ramírez MJ, Specht CD, Vogt L, Vos RA, Walls RL, White JW, Zhang G, Deans AR, Huala E, Lewis SE, Mabee PM. Emerging semantics to link phenotype and environment. PeerJ 2015; 3:e1470. [PMID: 26713234 PMCID: PMC4690371 DOI: 10.7717/peerj.1470] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2015] [Accepted: 11/12/2015] [Indexed: 11/20/2022] Open
Abstract
Understanding the interplay between environmental conditions and phenotypes is a fundamental goal of biology. Unfortunately, data that include observations on phenotype and environment are highly heterogeneous and thus difficult to find and integrate. One approach that is likely to improve the status quo involves the use of ontologies to standardize and link data about phenotypes and environments. Specifying and linking data through ontologies will allow researchers to increase the scope and flexibility of large-scale analyses aided by modern computing methods. Investments in this area would advance diverse fields such as ecology, phylogenetics, and conservation biology. While several biological ontologies are well-developed, using them to link phenotypes and environments is rare because of gaps in ontological coverage and limits to interoperability among ontologies and disciplines. In this manuscript, we present (1) use cases from diverse disciplines to illustrate questions that could be answered more efficiently using a robust linkage between phenotypes and environments, (2) two proof-of-concept analyses that show the value of linking phenotypes to environments in fishes and amphibians, and (3) two proposed example data models for linking phenotypes and environments using the extensible observation ontology (OBOE) and the Biological Collections Ontology (BCO); these provide a starting point for the development of a data model linking phenotypes and environments.
Collapse
Affiliation(s)
- Anne E. Thessen
- Ronin Institute for Independent Scholarship, Monclair, NJ, United States
- The Data Detektiv, Waltham, MA, United States
| | - Daniel E. Bunker
- Department of Biological Sciences, New Jersey Institute of Technology, Newark, NJ, United States
| | - Pier Luigi Buttigieg
- HGF-MPG Group for Deep Sea Ecology and Technology, Alfred-Wegener-Institut, Helmholtz-Zentrum für Polar-und Meeresforschung, Bremerhaven, Germany
| | - Laurel D. Cooper
- Department of Botany and Plant Pathology, Oregon State University, Corvallis, OR, United States
| | - Wasila M. Dahdul
- Department of Biology, University of South Dakota, Vermillion, SD, United States
| | - Sami Domisch
- Department of Ecology and Evolutionary Biology, Yale University, New Haven, CT, United States
| | - Nico M. Franz
- School of Life Sciences, Arizona State University, Tempe, AZ, United States
| | - Pankaj Jaiswal
- Department of Botany and Plant Pathology, Oregon State University, Corvallis, OR, United States
| | - Carolyn J. Lawrence-Dill
- Departments of Genetics, Development and Cell Biology and Agronomy, Iowa State University, Ames, IA, United States
| | | | | | - Martín J. Ramírez
- Division of Arachnology, Museo Argentino de Ciencias Naturales–CONICET, Buenos Aires, Argentina
| | - Chelsea D. Specht
- Departments of Plant and Microbial Biology & Integrative Biology, University of California, Berkeley, CA, United States
| | - Lars Vogt
- Institut für Evolutionsbiologie und Ökologie, Universität Bonn, Bonn, Germany
| | | | - Ramona L. Walls
- iPlant Collaborative, University of Arizona, Tucson, AZ, United States
| | - Jeffrey W. White
- US Arid Land Agricultural Research Center, United States Department of Agriculture—ARS, Maricopa, AZ, United States
| | - Guanyang Zhang
- School of Life Sciences, Arizona State University, Tempe, AZ, United States
| | - Andrew R. Deans
- Department of Entomology, Pennsylvania State University, University Park, PA, United States
| | - Eva Huala
- Phoenix Bioinformatics, Redwood City, CA, United States
| | - Suzanna E. Lewis
- Genomics Division, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
| | - Paula M. Mabee
- Department of Biology, University of South Dakota, Vermillion, SD, United States
| |
Collapse
|