Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain
The prediction of growing stock volume is one of the commonest applications of remote sensing to support the sustainable management of forest ecosystems. In this study, we used data from the 4th Spanish National Forest Inventory (SNFI-4) and from the 1st nationwide Airborne Laser Scanning (ALS) surv...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/14/1693 |
| _version_ | 1828143444444315648 |
|---|---|
| author | Alís Novo-Fernández Marcos Barrio-Anta Carmen Recondo Asunción Cámara-Obregón Carlos A. López-Sánchez |
| author_facet | Alís Novo-Fernández Marcos Barrio-Anta Carmen Recondo Asunción Cámara-Obregón Carlos A. López-Sánchez |
| author_sort | Alís Novo-Fernández |
| collection | DOAJ |
| description | The prediction of growing stock volume is one of the commonest applications of remote sensing to support the sustainable management of forest ecosystems. In this study, we used data from the 4th Spanish National Forest Inventory (SNFI-4) and from the 1st nationwide Airborne Laser Scanning (ALS) survey to develop predictive yield models for the three major commercial tree forest species (<i>Eucalyptus globulus</i>, <i>Pinus pinaster</i> and <i>Pinus radiata</i>) grown in north-western Spain. Integration of both types of data required prior harmonization because of differences in timing of data acquisition and difficulties in accurately geolocating the SNFI plots. The harmonised data from 477 <i>E.</i> globulus, 760 <i>P. pinaster</i> and 191 <i>P. radiata</i> plots were used to develop predictive models for total over bark volume, mean volume increment and total aboveground biomass by relating SNFI stand variables to metrics derived from the ALS data. The multiple linear regression methods and several machine learning techniques (k-nearest neighbour, random trees, random forest and the ensemble method) were compared. The study findings confirmed that multiple linear regression is outperformed by machine learning techniques. More specifically, the findings suggest that the random forest and the ensemble method slightly outperform the other techniques. The resulting stand level relative RMSEs for predicting total over bark volume, annual increase in total volume and total aboveground biomass ranged from 30.8−38.3%, 34.2−41.9% and 31.7−38.3% respectively. Although the predictions can be considered accurate, more precise geolocation of the SNFI plots and coincide temporarily with the ALS data would have enabled use of a much larger and robust field database to improve the overall accuracy of estimation. |
| first_indexed | 2024-04-11T19:57:19Z |
| format | Article |
| id | doaj.art-b07bb8d8d3cb4b8fa406870c4578a1ff |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:57:19Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b07bb8d8d3cb4b8fa406870c4578a1ff2022-12-22T04:05:57ZengMDPI AGRemote Sensing2072-42922019-07-011114169310.3390/rs11141693rs11141693Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western SpainAlís Novo-Fernández0Marcos Barrio-Anta1Carmen Recondo2Asunción Cámara-Obregón3Carlos A. López-Sánchez4Department of Organisms and Systems Biology, University of Oviedo, 33071 Oviedo, Asturias, SpainGIS-Forest Research Group, Department of Organisms and Systems Biology, University of Oviedo, Polytechnic School of Mieres, 33600 Mieres, Asturias, SpainRemote Sensing Applications Research Group (RSApps), Area of Cartographic, Geodesic and Photogrammetric Engineering, Department of Mining Exploitation and Prospecting, University of Oviedo, Gonzalo Gutiérrez Quirós s/n, 33600 Mieres, Asturias, SpainGIS-Forest Research Group, Department of Organisms and Systems Biology, University of Oviedo, Polytechnic School of Mieres, 33600 Mieres, Asturias, SpainGIS-Forest Research Group, Department of Organisms and Systems Biology, University of Oviedo, Polytechnic School of Mieres, 33600 Mieres, Asturias, SpainThe prediction of growing stock volume is one of the commonest applications of remote sensing to support the sustainable management of forest ecosystems. In this study, we used data from the 4th Spanish National Forest Inventory (SNFI-4) and from the 1st nationwide Airborne Laser Scanning (ALS) survey to develop predictive yield models for the three major commercial tree forest species (<i>Eucalyptus globulus</i>, <i>Pinus pinaster</i> and <i>Pinus radiata</i>) grown in north-western Spain. Integration of both types of data required prior harmonization because of differences in timing of data acquisition and difficulties in accurately geolocating the SNFI plots. The harmonised data from 477 <i>E.</i> globulus, 760 <i>P. pinaster</i> and 191 <i>P. radiata</i> plots were used to develop predictive models for total over bark volume, mean volume increment and total aboveground biomass by relating SNFI stand variables to metrics derived from the ALS data. The multiple linear regression methods and several machine learning techniques (k-nearest neighbour, random trees, random forest and the ensemble method) were compared. The study findings confirmed that multiple linear regression is outperformed by machine learning techniques. More specifically, the findings suggest that the random forest and the ensemble method slightly outperform the other techniques. The resulting stand level relative RMSEs for predicting total over bark volume, annual increase in total volume and total aboveground biomass ranged from 30.8−38.3%, 34.2−41.9% and 31.7−38.3% respectively. Although the predictions can be considered accurate, more precise geolocation of the SNFI plots and coincide temporarily with the ALS data would have enabled use of a much larger and robust field database to improve the overall accuracy of estimation.https://www.mdpi.com/2072-4292/11/14/1693national forest inventoryairborne laser scanningforest yieldregressionmachine learning techniques |
| spellingShingle | Alís Novo-Fernández Marcos Barrio-Anta Carmen Recondo Asunción Cámara-Obregón Carlos A. López-Sánchez Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain Remote Sensing national forest inventory airborne laser scanning forest yield regression machine learning techniques |
| title | Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain |
| title_full | Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain |
| title_fullStr | Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain |
| title_full_unstemmed | Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain |
| title_short | Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain |
| title_sort | integration of national forest inventory and nationwide airborne laser scanning data to improve forest yield predictions in north western spain |
| topic | national forest inventory airborne laser scanning forest yield regression machine learning techniques |
| url | https://www.mdpi.com/2072-4292/11/14/1693 |
| work_keys_str_mv | AT alisnovofernandez integrationofnationalforestinventoryandnationwideairbornelaserscanningdatatoimproveforestyieldpredictionsinnorthwesternspain AT marcosbarrioanta integrationofnationalforestinventoryandnationwideairbornelaserscanningdatatoimproveforestyieldpredictionsinnorthwesternspain AT carmenrecondo integrationofnationalforestinventoryandnationwideairbornelaserscanningdatatoimproveforestyieldpredictionsinnorthwesternspain AT asuncioncamaraobregon integrationofnationalforestinventoryandnationwideairbornelaserscanningdatatoimproveforestyieldpredictionsinnorthwesternspain AT carlosalopezsanchez integrationofnationalforestinventoryandnationwideairbornelaserscanningdatatoimproveforestyieldpredictionsinnorthwesternspain |