Asset Details
Do you wish to reserve the book?
Assessing the Capacities of Different Remote Sensors in Estimating Forest Stock Volume Based on High Precision Sample Plot Positioning and Random Forest Method
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Assessing the Capacities of Different Remote Sensors in Estimating Forest Stock Volume Based on High Precision Sample Plot Positioning and Random Forest Method
Do you wish to request the book?
Assessing the Capacities of Different Remote Sensors in Estimating Forest Stock Volume Based on High Precision Sample Plot Positioning and Random Forest Method
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Publication
Assessing the Capacities of Different Remote Sensors in Estimating Forest Stock Volume Based on High Precision Sample Plot Positioning and Random Forest Method
2022
Overview
Forest stock volume (FSV) is an important forest resource indicator. Satellite images from various sensors have been used to estimate FSV. However, there is still a lack of comparative studies on the estimation of FSV with remote sensing data obtained by different sensors. In addition, there is a lack of high-precision ground sample positioning methods, which can improve the matching of ground data and remote sensing data to a certain extent, and improve the estimation accuracy. In this research, a new ground sample plot positioning method was proposed, which could achieve sub-meter positioning accuracy in forest areas, greatly improving the matching accuracy of ground sample plot data and remote sensing data. Based on this high-precision positioning method and the random forest algorithm, we compared and quantified the ability of different sensors to estimate the FSV. The results by random forest modeling showed that the images from a single sensor, Sentinel-2, performed best in the test dataset (R2 = 0.57, RMSE = 70.12 m3 ha-1). For the data from two sensors, the best performance was achieved by the combined Sentinel-2 and PALSAR2/PALSAR data, which had an R2 of 0.62 with RMSE of 65.51 m3 ha-1 in the validation data. The images from the three sensors, Sentinel-2, Landsat-8, and PALSAR2/PALSAR, achieved a modeling accuracy of R2 (0.62) and RMSE (65.40 m3 ha-1). The results clearly showed the capacity of the different sensor data to estimate FSV based on the high precision sample plot positioning method, and it will help forest researchers investigate and estimate the FSV in the future.
