{"title":"利用多源遥感数据对伊朗针叶人工林的森林地上生物量进行深度和机器学习预测","authors":"Hassan Ali, Jahangir Mohammadi, Shaban Shataee Jouibary","doi":"10.1007/s10342-024-01721-w","DOIUrl":null,"url":null,"abstract":"<p>Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R<sup>2</sup> using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R<sup>2</sup> using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R<sup>2</sup>).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.</p>","PeriodicalId":11996,"journal":{"name":"European Journal of Forest Research","volume":"232 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran\",\"authors\":\"Hassan Ali, Jahangir Mohammadi, Shaban Shataee Jouibary\",\"doi\":\"10.1007/s10342-024-01721-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R<sup>2</sup> using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R<sup>2</sup> using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R<sup>2</sup>).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.</p>\",\"PeriodicalId\":11996,\"journal\":{\"name\":\"European Journal of Forest Research\",\"volume\":\"232 1\",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Forest Research\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1007/s10342-024-01721-w\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"FORESTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Forest Research","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s10342-024-01721-w","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FORESTRY","Score":null,"Total":0}
Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran
Above-ground biomass (AGB) is one of the most popular forest attribute used to estimating, monitoring and evaluating global carbon storage. Accurately estimating AGB is one of the most significant steps in decision-making regarding sustainable forest management, climate policy and management efficiency. Thus, developing accurate AGB estimation models using satellite data is essential. In the present study, the capability of Phased array type L-band synthetic aperture radar (ALOS-PALSAR) and SPOT-6 data to model AGB using Deep learning (DL) and Random forest (RF) and Multiple linear regression (MLR) algorithms were evaluated in coniferous planted area, northern Iran. The systematic cluster sampling method was applied to collect field plot data. A total of 180 circular plots were measured to calculate AGB per hectare. The DL, RF and MLR algorithms were used for AGB modeling. The relative root mean squared error (rRMSE) and R2 using ALOS-PALSAR data were 21.99% and 0.21 for the DL, 48.46% and 0.18 for RF and 50.20% and 0.11 for MLR, respectively. Also, the RMSE% and R2 using SPOT-6 data were 18.31% and 0.44 for DL, 39.64% and 0.43 for the RF and 44.08% and 0.38 for MLR, respectively. Compared to modeling AGB using ALOS-PALSAR and SPOT-6 data separately, the combination of ALOS-PALSAR and SPOT-6 improved AGB prediction (1.14–23% decrease in RMSE% and 0.11–0.33 increase in R2).The results showed that using of DL provided an increase in prediction accuracy compared to RF and MLR. Based on the results, we conclude that modeling AGB using a combination of ALOS-PALSAR and SPOT-6 data and DL can be useful for estimating AGB in the coniferous planted forests.
期刊介绍:
The European Journal of Forest Research focuses on publishing innovative results of empirical or model-oriented studies which contribute to the development of broad principles underlying forest ecosystems, their functions and services.
Papers which exclusively report methods, models, techniques or case studies are beyond the scope of the journal, while papers on studies at the molecular or cellular level will be considered where they address the relevance of their results to the understanding of ecosystem structure and function. Papers relating to forest operations and forest engineering will be considered if they are tailored within a forest ecosystem context.