Improved remote sensing methods to detect northern wild rice (Zizania palustris L.)
Declining populations of Zizania palustris L. (northern wildrice, or wildrice) during the last century drives the demand for new and innovative techniques to support monitoring of this culturally and ecologically significant crop wild relative. We trained three wildrice detection models in R and...
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
MDPI
2020
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/109587 |
| _version_ | 1855534870179086336 |
|---|---|
| author | O’Shea, Kristen LaRoe, Jillian Vorster, Anthony Young, Nicholas Evangelista, Paul Mayer, Timothy Carver, Daniel Simonson, Eli Martin, Vanesa Radomski, Paul Knopik, Joshua Kern, Anthony Khoury, Colin K. |
| author_browse | Carver, Daniel Evangelista, Paul Kern, Anthony Khoury, Colin K. Knopik, Joshua LaRoe, Jillian Martin, Vanesa Mayer, Timothy O’Shea, Kristen Radomski, Paul Simonson, Eli Vorster, Anthony Young, Nicholas |
| author_facet | O’Shea, Kristen LaRoe, Jillian Vorster, Anthony Young, Nicholas Evangelista, Paul Mayer, Timothy Carver, Daniel Simonson, Eli Martin, Vanesa Radomski, Paul Knopik, Joshua Kern, Anthony Khoury, Colin K. |
| author_sort | O’Shea, Kristen |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Declining populations of Zizania palustris L. (northern wildrice, or wildrice) during
the last century drives the demand for new and innovative techniques to support monitoring of
this culturally and ecologically significant crop wild relative. We trained three wildrice detection
models in R and Google Earth Engine using data from annual aquatic vegetation surveys in
northern Minnesota. Three di erent training datasets, varying in the definition of wildrice presence,
were combined with Landsat 8 Operational Land Imager (OLI) and Sentinel-1 C-band synthetic
aperture radar (SAR) imagery to map wildrice in 2015 using random forests. Spectral predictors
were derived from phenologically important time periods of emergence (June–July) and peak harvest
(August–September). The range of the Vertical Vertical (VV) polarization between the two time
periods was consistently the top predictor. Model outputs were evaluated using both point and
area-based validation (polygon). While all models performed well in the point validation with
percent correctly classified ranging from 83.8% to 91.1%, we found polygon validation necessary to
comprehensively assess wildrice detection accuracy. Our practical approach highlights a variety of
applications that can be applied to guide field excursions and estimate the extent of occurrence at
landscape scales. Further testing and validation of the methods we present may support multiyear
monitoring which is foundational for the preservation of wildrice for future generations. |
| format | Journal Article |
| id | CGSpace109587 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2020 |
| publishDateRange | 2020 |
| publishDateSort | 2020 |
| publisher | MDPI |
| publisherStr | MDPI |
| record_format | dspace |
| spelling | CGSpace1095872025-11-11T19:01:57Z Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) O’Shea, Kristen LaRoe, Jillian Vorster, Anthony Young, Nicholas Evangelista, Paul Mayer, Timothy Carver, Daniel Simonson, Eli Martin, Vanesa Radomski, Paul Knopik, Joshua Kern, Anthony Khoury, Colin K. zizania wild plants crops acquatic environment vegetation surveys modelling computer applications remote sensing modelizacion teledeteccion Declining populations of Zizania palustris L. (northern wildrice, or wildrice) during the last century drives the demand for new and innovative techniques to support monitoring of this culturally and ecologically significant crop wild relative. We trained three wildrice detection models in R and Google Earth Engine using data from annual aquatic vegetation surveys in northern Minnesota. Three di erent training datasets, varying in the definition of wildrice presence, were combined with Landsat 8 Operational Land Imager (OLI) and Sentinel-1 C-band synthetic aperture radar (SAR) imagery to map wildrice in 2015 using random forests. Spectral predictors were derived from phenologically important time periods of emergence (June–July) and peak harvest (August–September). The range of the Vertical Vertical (VV) polarization between the two time periods was consistently the top predictor. Model outputs were evaluated using both point and area-based validation (polygon). While all models performed well in the point validation with percent correctly classified ranging from 83.8% to 91.1%, we found polygon validation necessary to comprehensively assess wildrice detection accuracy. Our practical approach highlights a variety of applications that can be applied to guide field excursions and estimate the extent of occurrence at landscape scales. Further testing and validation of the methods we present may support multiyear monitoring which is foundational for the preservation of wildrice for future generations. 2020-09-16 2020-09-22T22:27:13Z 2020-09-22T22:27:13Z Journal Article https://hdl.handle.net/10568/109587 en Open Access application/pdf MDPI O’Shea, K.; LaRoe, J.; Vorster, A.; Young, N.; Evangelista, P.; Mayer, T.; Carver, D.; Simonson, E.; Martin, V.; Radomski, P.; Knopik, J.; Kern, A.; Khoury, C.K. (2020) Improved remote sensing methods to detect northern wild rice (Zizania palustris L.). Remote Sensing 12(3023) 18 p. ISSN: 2072-4292 |
| spellingShingle | zizania wild plants crops acquatic environment vegetation surveys modelling computer applications remote sensing modelizacion teledeteccion O’Shea, Kristen LaRoe, Jillian Vorster, Anthony Young, Nicholas Evangelista, Paul Mayer, Timothy Carver, Daniel Simonson, Eli Martin, Vanesa Radomski, Paul Knopik, Joshua Kern, Anthony Khoury, Colin K. Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title | Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title_full | Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title_fullStr | Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title_full_unstemmed | Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title_short | Improved remote sensing methods to detect northern wild rice (Zizania palustris L.) |
| title_sort | improved remote sensing methods to detect northern wild rice zizania palustris l |
| topic | zizania wild plants crops acquatic environment vegetation surveys modelling computer applications remote sensing modelizacion teledeteccion |
| url | https://hdl.handle.net/10568/109587 |
| work_keys_str_mv | AT osheakristen improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT laroejillian improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT vorsteranthony improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT youngnicholas improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT evangelistapaul improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT mayertimothy improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT carverdaniel improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT simonsoneli improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT martinvanesa improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT radomskipaul improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT knopikjoshua improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT kernanthony improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl AT khourycolink improvedremotesensingmethodstodetectnorthernwildricezizaniapalustrisl |