Automated detection of individual clove trees for yield quantification in northeastern Madagascar based on multi-spectral satellite data
| Autor: | Sandra I.B. Roth, Reik Leiterer, Michael E. Schaepman, Enrico Celio, Michele Volpi, Philip C. Joerg |
|---|---|
| Přispěvatelé: | University of Zurich, Roth, Sandra I B |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
010504 meteorology & atmospheric sciences
0208 environmental biotechnology Soil Science Multi spectral Clove bud yield estimation 02 engineering and technology Circular Hough transform 01 natural sciences law.invention law Satellite data Statistics 910 Geography & travel Computers in Earth Sciences Single tree detection Tree species classification LULC classification Random forest Very high-resolution satellite image Pléiades satellite Essential oil 1111 Soil Science 1907 Geology 0105 earth and related environmental sciences Remote sensing Crop yield 1903 Computers in Earth Sciences Geology 020801 environmental engineering 10122 Institute of Geography Classification methods Tree species |
| Zdroj: | Remote Sensing of Environment, 221 |
| ISSN: | 0034-4257 |
| DOI: | 10.3929/ethz-b-000307585 |
| Popis: | There is an increasing demand for clove products, mainly dried buds and essential oil on global markets. Consequently, the importance of clove trees as a provisioning service is increasing at the local level, particularly for smallholders cultivating clove trees as cash crops. Due to limited availability of data on local production, using remote sensing-based methods to quantify today's clove production is of key interest. We estimated the clove bud yield in a study site in northeastern Madagascar by detecting individual clove trees and determining relevant production systems, including pasture and clove, clove plantation and agroforestry systems. We implemented an individual tree detection method based on two machine learning approaches. Specifically, we proposed using a circular Hough transform (CHT) for the automated detection of individual clove trees. Subsequently, we implemented a tree species classification method using a random forests (RF) classifier based on a set of features extracted for relevant trees in the above production systems. Finally, we classified and mapped different production systems. Based on the number of detected clove trees growing in a clove production system, we estimated the production system-dependent clove bud yield. Our results show that 97.9% of all reference clove trees were detected using a CHT. Classifying clove and non-clove trees resulted in a producer accuracy of 70.7% and a user accuracy of 59.2% for clove trees. The classification of the clove production systems resulted in an overall accuracy of 77.9%. By averaging different clove tree yield estimates obtained from the literature, we estimated an average total yield of approximately 575 tons/year for our 25,600 ha study area. With this approach, we demonstrate a first step towards large-scale clove bud yield estimation using remote sensing data and methodologies. Remote Sensing of Environment, 221 ISSN:0034-4257 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect