Monitoring Canopy Height in the Hainan Tropical Rainforest Using Machine Learning and Multi-Modal Data Fusion

Forest canopy height is defined as the distance between the highest point of the tree canopy and the ground, which is considered to be a key factor in calculating above-ground biomass, leaf area index, and carbon stock. Large-scale forest canopy height monitoring can provide scientific information on deforestation and forest degradation to policymakers. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) was launched in 2018, with the Advanced Topographic Laser Altimeter System (ATLAS) instrument taking on the task of mapping and transmitting data as a photon-counting LiDAR, which offers an opportunity to obtain global forest canopy height. To generate a high-resolution forest canopy height map of Jiangxi Province, we integrated ICESat-2 and multi-source remote sensing imagery, including Sentinel-1, Sentinel-2, the Shuttle Radar Topography Mission, and forest age data of Jiangxi Province. Meanwhile, we develop four canopy height extrapolation models by random forest (RF), Support Vector Machine (SVM), K-nearest neighbor (KNN), Gradient Boosting Decision Tree (GBDT) to link canopy height in ICESat-2, and spatial feature information in multi-source remote sensing imagery. The results show that: (1) Forest canopy height is moderately correlated with forest age, making it a potential predictor for forest canopy height mapping. (2) Compared with GBDT, SVM, and KNN, RF showed the best predictive performance with a coefficient of determination (R2) of 0.61 and a root mean square error (RMSE) of 5.29 m. (3) Elevation, slope, and the red-edge band (band 5) derived from Sentinel-2 were significantly dependent variables in the canopy height extrapolation model. Apart from that, Forest age was one of the variables that the RF moderately relied on. In contrast, backscatter coefficients and texture features derived from Sentinel-1 were not sensitive to canopy height. (4) There is a significant correlation between forest canopy height predicted by RF and forest canopy height measured by field measurements (R2 = 0.69, RMSE = 4.02 m). In a nutshell, the results indicate that the method utilized in this work can reliably map the spatial distribution of forest canopy height at high resolution.

Forest canopy height is an important indicator of the forest ecosystem, and an accurate assessment of forest canopy height on a large scale is of great significance for forest resource quantification and carbon sequestration. The retrieval of canopy height based on remote sensing provides a possibility for studying forest ecosystems. This study proposes a new method for estimating forest canopy height based on remote sensing. In this method, the GEDI satellite and ICESat-2 satellite, which are different types of space-borne lidar products, are used to cooperate with the Landsat 9 image and SRTM terrain data, respectively. Two forest canopy height-retrieval models based on multi-source remote sensing integration are obtained using a random forest regression (RFR) algorithm. The study, conducted at a forest site in the northeastern United States, synthesized various remote sensing data sets to produce a robust canopy height model. First, we extracted relative canopy height products, multispectral features, and topographic data from GEDI, ICESat-2, Landsat 9, and SRTM images, respectively. The importance of each variable was assessed, and the random forest algorithm was used to analyze each variable statistically. Then, the random forest regression algorithm was used to combine these variables and construct the forest canopy height model. Validation with airborne laser scanning (ALS) data shows that the GEDI and ICESat-2 models using a single data source achieve better accuracy than the Landsat 9 model. Notably, the combination of GEDI, Landsat 9, and SRTM data (R = 0.92, MAE = 1.91 m, RMSE = 2.78 m, and rRMSE = 12.64%) and a combination of ICESat-2, Landsat 9, and SRTM data (R = 0.89, MAE = 1.84 m, RMSE = 2.54 m, and rRMSE = 10.75%). Compared with the least accurate Landsat 9 model, R increased by 29.58%, 93.48%, MAE by 44.64%, 46.20%, RMSE by 42.80%, 49.40%, and the rRMSE was increased by 42.86% and 49.32%, respectively. These results fully evaluate and discuss the practical performance and benefits of multi-source data retrieval of forest canopy height by combining space-borne lidar data with Landsat 9 data, which is of great significance for understanding forest structure and dynamics. The study provides a reliable methodology for estimating forest canopy height and valuable insights into forest resource management and its contribution to global climate change.

Continuous and extensive monitoring of forest height is essential for estimating forest above-ground biomass and predicting the ability of forests to absorb CO2. In particular, forest height at the national scale is an important indicator reflecting the national forestry economic construction, environmental governance, and ecological balance. However, the lack of inventory data restricts large-scale monitoring of forest height to some extent. Conducting manual surveys of forest height for large-scale areas would be labor-intensive and time-consuming. The successful launch of the new generation of spaceborne light detection and ranging (LiDAR) (The Ice, Cloud, and Land Elevation Satellite-2/the Advanced Topographic Laser Altimeter System, ICESat-2/ATLAS) has brought new opportunities for national-scale forestry resource surveys. This paper explores a method to survey national forest canopy height from the new generation of ICESat-2/ATLAS data. In view of the sparse sampling and little overlap between repeated spaceborne LiDAR data, a strategy for assessing the overall change of canopy height for large scales is provided. Some spatially continuous ancillary data were used to assist ICESat-2/ATLAS data to generate a wall-to-wall (spatially continuous) forest canopy height map in China by using the machine learning approach and then quantifying the analysis of forest canopy height in various provinces. The results show that there is a good correlation between the model forest height and the verification data, with a root mean squared error (RMSE) of 3.30 m and a coefficient of determination (R2) of 0.87. This indicates that the method for retrieving national forest canopy height is reliable. There are some limitations in areas with lower vegetation coverage or complex topography which need additional filtering or terrain correction to achieve higher accuracy in measuring forest canopy height. Our analysis suggests that ICESat-2/ATLAS data can achieve the retrieval of national forest height at an overall level, and it would be feasible to use ICESAT-2/ATLAS products to estimate forest canopy height change for large-scale areas.

Light Detection and Ranging (LiDAR) system has a unique capability for estimating accurately forest canopy height, which has a direct relationship and can provide better understanding to the aboveground carbon storage. This study aimed to test the capacity of large-footprint full waveform LiDAR for estimating forest canopy height and aboveground biomass in the cool temperate forest over sloped terrain. The full waveform data of the Geoscience Laser Altimeter System (GLAS) onboard the Ice, Cloud, and land Elevation Satellite (ICESat) was used to achieve the aim in Wangqing of Changbai Mountain. The maximum canopy height was first regressed as a function of waveform extent and the elevation change for evaluating the Lefsky's model. Then an improved model of maximum forest canopy height against the logarithm of waveform extent and the elevation change was tested for improving the accuracy of forest canopy height estimation. Finally the aboveground forest biomass was related to ICESat-derived maximum canpy height from the improved model. The results showed that the Lefsky's model and the improved model explained 51% and 74% of variation of maximum canopy height for the terrain slope range of 0~15°, respectively, and the improved model performed better than the Lefsky's model for estimating forest maximum canopy height over the sloped terrain. The ICESat-derived maximum canpy height from the improved model explained 52% of variation of the aboveground forest biomass. The results indicated that the ICESat-GLAS full waveforms are promising for estimating maximum forest canopy height and aboveground biomass in the study area.

The present study aims to map forest canopy height by integrating ICESat‐2 and Sentinel‐1 data and investigate the effect of integrating forest canopy height information with Sentinel‐2 data‐derived spectral variables on the prediction of spatial distribution of forest aboveground biomass (AGB). Random forest (RF) algorithm was used to develop forest canopy height and AGB models. It was observed that ICESat‐2 and Sentinel‐1 based model was able to predict forest canopy height with R2 = 0.84 and %RMSE = 4.48%. Two forest AGB models were developed, with only spectral variables and by incorporating forest height information with spectral variables. The results reflected that incorporation of forest canopy height in the forest AGB model improved the accuracy of the AGB predictions (R2 = 0.83, %RMSE = 4.64%). The study presents a comprehensive methodology for mapping forest canopy height and AGB.

The availability of phosphorus (P) can limit net primary production (NPP) in tropical rainforests growing on highly weathered soils. Although it is well known that plant roots release organic acids to acquire P from P-deficient soils, the importance of organic acid exudation in P-limited tropical rainforests has rarely been verified. Study sites were located in two tropical montane rainforests (a P-deficient older soil and a P-rich younger soil) and a tropical lowland rainforest on Mt. Kinabalu, Borneo to analyze environmental control of organic acid exudation with respect to soil P availability, tree genus, and NPP. We quantified root exudation of oxalic, citric, and malic acids using in situ methods in which live fine roots were placed in syringes containing nutrient solution. Exudation rates of organic acids were greatest in the P-deficient soil in the tropical montane rainforest. The carbon (C) fluxes of organic acid exudation in the P-deficient soil (0.7 mol C m−2 month−1) represented 16.6% of the aboveground NPP, which was greater than those in the P-rich soil (3.1%) and in the lowland rainforest (4.7%), which exhibited higher NPP. The exudation rates of organic acids increased with increasing root surface area and tip number. A shift in vegetation composition toward dominance by tree species exhibiting a larger root surface area might contribute to the higher organic acid exudation observed in P-deficient soil. Our results quantitatively showed that tree roots can release greater quantities of organic acids in response to P deficiency in tropical rainforests.

There have been conflicting findings on hydrological dynamics in tropical montane cloud forests (TMCFs)—attributed to differences in climate, altitude, topography, and vegetation. We contribute another observation-based comparison between a TMCF (8.53 ha; 1906 m.a.s.l.) and a tropical lowland rainforest (TLRF) (5.33 ha; 484 m.a.s.l.) catchment in equatorial Sabah, Malaysian Borneo. In each catchment, a 90° v-notch weir was established at the stream’s outlet and instrumented with a water-level datalogger that records data at 10-min intervals (converted to discharge). A nearby meteorological station records rainfall at the same 10-min intervals via a tipping bucket rain gauge connected to a datalogger. Over five years, 91 and 73 storm hydrographs from a TMCF and a TLRF, respectively, were extracted and compared. Various hydrograph metrices relating to discharge and flashiness were compared between the TMCF and TLRF while controlling for event rainfall, rainfall intensity, and antecedent moisture. Compared to the TLRF, storm-event runoff in the TMCF was up to 169% higher, reflecting the saturated conditions and tendency for direct runoff. Instantaneous peak discharge was also higher (up to 6.6x higher) in the TMCF. However, despite high moisture and steep topography, stream responsiveness towards rainfall input was lower in the TMCF, which we hypothesise was due to its wide and short catchment dimensions. Baseflow was significantly correlated with API20, API10, and API7. Overall, we found that the TMCF had higher runoff, but higher moisture condition alone may not be sufficient to govern flashiness.

Spaceborne LiDAR has been widely used to obtain forest canopy heights over large areas, but it is still a challenge to obtain spatio-continuous forest canopy heights with this technology. In order to make up for this deficiency and take advantage of the complementary for multi-source remote sensing data in forest canopy height mapping, a new method to estimate forest canopy height was proposed by synergizing the spaceborne LiDAR (ICESat-2) data, Synthetic Aperture Radar (SAR) data, multi-spectral images, and topographic data considering forest types. In this study, National Geographical Condition Monitoring (NGCM) data was used to extract the distributions of coniferous forest (CF), broadleaf forest (BF), and mixed forest (MF) in Hua’ nan forest area in Heilongjiang Province, China. Accordingly, the forest canopy height estimation models for whole forest (all forests together without distinguishing types, WF), CF, BF, and MF were established, respectively, by Radom Forest (RF) and Gradient Boosting Decision Tree (GBDT). The accuracy for established models and the forest canopy height obtained based on estimation models were validated consequently. The results showed that the forest canopy height estimation models considering forest types had better performance than the model grouping all types of forest together. Compared with GBDT, RF with optimal variables had better performance in forest canopy height estimation with Pearson’s correlation coefficient (R) and the root-mean-squared error (RMSE) values for CF, BF, and MF of 0.72, 0.59, 0.62, and 3.15, 3.37, 3.26 m, respectively. It has been validated that a synergy of ICESat-2 with other remote sensing data can make a crucial contribution to spatio-continuous forest canopy height mapping, especially for areas covered by different types of forest.

Forest canopy height mapping is critical for mapping and modeling bio-geophysical and ecological factors, including forest aboveground biomass, carbon reserves, forest carbon emissions, habitat diversity, forest degradation, and restoration success. The Global Ecosystem Dynamics Investigation (GEDI) is a spaceborne Light Detection and Ranging (LiDAR) sensor designed specifically to collect data on forest ecosystems worldwide. However, the information obtained by GEDI is not wall-to-wall, requiring data fusion approaches to map spatially continuous canopy heights. This study, for the first time, presents canopy height models for the entire country of Nepal based on interpolated GEDI tree heights fusing Sentinel-2 multispectral imagery with Sentinel-1 synthetic aperture radar (SAR), creating species-specific continuous canopy height models for Nepal at 10 m resolution. Forest plot field data, collected from a nationwide campaign, provided data on species identity, which was used for species mapping and accuracy evaluation. Differences in canopy-architecture and leaf-level traits mean that species-specific models are needed to interpolate GEDI tree heights using the Sentinel optical and SAR data. The national forest height map was compared with an independent set of GEDI data (RMSE = 2.4 m, R 2 = 0.92, intercept (c) = 0.53 m and slope (m) = 0.98) and fully independent field data (RMSE = 3.7 m, R 2 = 0.74, c = 4.1 m, and m = 0.89). The developed forest type map and canopy height models have the potential to aid in both operational monitoring and hindcasting of historical forest height and its dynamics. Local and national forest management initiatives and international climate and sustainable development projects require this kind of capacity.

Forest canopy height is a fundamental parameter of forest structure, and plays a pivotal role in understanding forest biomass allocation, carbon stock, forest productivity, and biodiversity. Spaceborne LiDAR (Light Detection and Ranging) systems, such as GEDI (Global Ecosystem Dynamics Investigation), provide large-scale estimation of ground elevation, canopy height, and other forest parameters. However, these measurements may have uncertainties influenced by topographic factors. This study focuses on the calibration of GEDI L2A and L1B data using an airborne LiDAR point cloud, and the combination of Sentinel-2 multispectral imagery, 1D convolutional neural network (CNN), artificial neural network (ANN), and random forest (RF) for upscaling estimated forest height in the Guangxi Gaofeng Forest Farm. First, various environmental (i.e., slope, solar elevation, etc.) and acquisition parameters (i.e., beam type, Solar elevation, etc.) were used to select and optimize the L2A footprint. Second, pseudo-waveforms were simulated from the airborne LiDAR point cloud and were combined with a 1D CNN model to calibrate the L1B waveform data. Third, the forest height extracted from the calibrated L1B waveforms and selected L2A footprints were compared and assessed, utilizing the CHM derived from the airborne LiDAR point cloud. Finally, the forest height data with higher accuracy were combined with Sentinel-2 multispectral imagery for an upscaling estimation of forest height. The results indicate that through optimization using environmental and acquisition parameters, the ground elevation and forest canopy height extracted from the L2A footprint are generally consistent with airborne LiDAR data (ground elevation: R2 = 0.99, RMSE = 4.99 m; canopy height: R2 = 0.42, RMSE = 5.16 m). Through optimizing, ground elevation extraction error was reduced by 45.5% (RMSE), and the canopy height extraction error was reduced by 30.3% (RMSE). After training a 1D CNN model to calibrate the forest height, the forest height information extracted using L1B has a high accuracy (R2 = 0.84, RMSE = 3.13 m). Compared to the optimized L2A data, the RMSE was reduced by 2.03 m. Combining the more accurate L1B forest height data with Sentinel-2 multispectral imagery and using RF and ANN for the upscaled estimation of the forest height, the RF model has the highest accuracy (R2 = 0.64, RMSE = 4.59 m). The results show that the extrapolation and inversion of GEDI, combined with multispectral remote sensing data, serve as effective tools for obtaining forest height distribution on a large scale.

Tropical Montane Cloud Forests (TMCF) have unique hydrology considering their high moisture, steep headwater terrain, shallow soils, frequent precipitation, and the presence of horizontal precipitation. While the hydrology of Tropical Lowland Rainforests (TLRF) has been given due attention, TMCF in Malaysia have been less explored. This study compares stream responsiveness and peak flow dynamics between TLRF (substation Inobong, 5.33 ha) and TMCF (substation Alab, 8.53 ha) in Crocker Range, Sabah, Malaysia. Streams in both study site were instrumented with water level sensors and dataloggers, and meteorological stations that records data at 10-minute intervals. Two hydrograph metrices namely T res (time taken from start of precipitation to hydrograph initiation) and T peak (time taken from start of hydrograph response to peak discharge) were assessed via a combination of the Mann-Whitney test and ANCOVA. TMCF took a longer time to achieve peak water level (mean T peak=143 mins) compared to TLRF (mean T peak=118 mins). Average rainfall intensity (P i) was negatively correlated with T peak. T res was higher in TMCF (mean=141 mins) than in TLRF (mean=51 mins) and was not affected by P or P i. Understanding such hydrological dynamics in TMCF is important for better headwater resource management and for flood prevention.

Xishuangbanna, located in south Yunnan, southwest China, is the northern border of the tropical zone. It maintains large areas of tropical rainforest called tropical seasonal rainforest. Like most tropical rainforests all over the world, these tropical seasonal rainforests are under high pressure of long_term disturbance caused by forest utilization. Amomum villosum, a shade_tolerant perennial herb, prefers to grow in forest gaps. It is one of the main cash crops of local people as its fruit is widely used in Chinese traditional medicine. It has been widely planted in tropical seasonal rainforest understorey in Xishuangbanna. To promote its growth and fruit yield by raising the light level of habitat, the forest shrub and herb layers are cleaned and about 60% 70% of trees are thinned. As a result, A. villosum planting has become the most serious disturbance to the tropical seasonal rainforest. Net primary productivity ( NPP ) is the primary element of nutrient cycling and energy flow within an ecosystem. It reflects the ability of a plant community to use natural resources. Most of the studies on forest NPP change after disturbance have focused on secondary forest, and few studies report the impact on NPP of forest canopy damage. This paper aims to determine the effect of A. villosum planting on forest NPP , and to study if that disturbance is the current most important limiting factor on NPP of the rainforest in Xishuangbanna. The study was carried out at Menglun, Xishuangbanna. Three primary seasonal rainforest sites and three disturbed rainforest sites with A. villosum plantation were chosen for the study and one 0.25 hm 2 plot was established at each site. All six study sites were distributed along ravines, within 21°55′ 21°59′N,101°08′ 101°13′E and at altitude of 650 800 m. Pometia tomentosa is the dominant tree species of the top tree layers at all research sites. At each plot, all trees and lianas with diameter at breast height ( DBH ) ≥5 cm were numbered and marked at breast height, and their DBH were measured annually. The biomass ( B ) and its annual increment ( ΔB ) of the research plots was estimated using the allometric regression equation relating tree mass to DBH of Xishuangbanna tropical rainforest. The amount of dead wood on all plots was recorded annually. At the same time, 20 litter fall traps were placed at each plot and litter was collected every half month. Leaf herbivory was measured by leaf samples and the total leaf herbivory ( G ) was estimated through annual leaf litterfall. The primary net productivity was calculated using the NPP equation NPP = ΔB+L+G, in which L is annual litterfall together with dead wood. The shrub and herb biomass were determined by the harvest method and their biomass increment was estimated by biomass divided by age. The biomass increment for shrub and herb was approximate to NPP . The results show that the annual mean NPP (mean±SE) of the primary rainforest is 23.47±2.12 t·hm -2 ·a -1 , with 22.04±2.09 t·hm -2 ·a -1 in the tree layer, 0.75±0.08 t·hm -2 ·a -1 in the shrub layer, 0.43±0.05 t·hm -2 ·a -1 in woody liana and 0.25±0.03 t·hm -2 ·a -1 in the herb layer. The allocation of NPP of the tree layer was: for litterfall, 11.75±0.54 t·hm -2 ·a -1 ; for tree fall, 0.62±0.21 t·hm -2 ·a -1 ; for leaf herbivory, 0.66±0.05 t·hm -2 ·a -1 ; and for biomass accumulation, 9.01±2.70 t·hm -2 ·a -1 . Compared to the primary rainforest, the NPP of the tree layer, shrub layer, woody liana and total community of the disturbed rainforest decreased 26.1%, 65.7%, 86.1% and 22.5% respectively, but the herb NPP increased 536% because of the dominance of A. villosum. Similarly, litterfall and biomass accumulation of the tree layer decreased 25.5% and 53.4% respectively. The tree fall increased 356% relative to the primary forest due to the change of microenvironment after disturb

Forest canopy height plays an important role in forest resource management and conservation. The accurate estimation of forest canopy height on a large scale is important for forest carbon stock, biodiversity, and the carbon cycle. With the technological development of satellite-based LiDAR, it is possible to determine forest canopy height over a large area. However, the forest canopy height that is acquired by this technology is influenced by topography and climate, and the canopy height that is acquired in complex subtropical mountainous regions has large errors. In this paper, we propose a method for estimating forest canopy height by combining long-time series Landsat images with GEDI satellite-based LiDAR data, with Fujian, China, as the study area. This approach optimizes the quality of GEDI canopy height data in topographically complex areas by combining stand age and tree height, while retaining the advantage of fast and effective forest canopy height measurements with satellite-based LiDAR. In this study, the growth curves of the main forest types in Fujian were first obtained by using a large amount of forest survey data, and the LandTrendr algorithm was used to obtain the forest age distribution in 2020. The obtained forest age was then combined with the growth curves of each forest type in order to determine the tree height distribution. Finally, the obtained average tree heights were merged with the GEDI_V27 canopy height product in order to create a modified forest canopy height model (MGEDI_V27) with a 30 m spatial resolution. The results showed that the estimated forest canopy height had a mean of 15.04 m, with a standard deviation of 4.98 m. In addition, we evaluated the accuracy of the GEDI_V27 and the MGEDI_V27 using the sample dataset. The MGEDI_V27 had a higher accuracy (R2 = 0.67, RMSE = 2.24 m, MAE = 1.85 m) than the GEDI_V27 (R2 = 0.39, RMSE = 3.35 m, MAE = 2.41 m). R2, RMSE, and MAE were improved by 71.79%, 33.13%, and 22.53%, respectively. We also produced a forest age distribution map of Fujian for the year 2020 and a forest disturbance map of Fujian for the past 32 years. The research results can provide decision support for forest ecological protection and management and for carbon sink analysis in Fujian.

Forest canopy height is an important parameter for studying biodiversity and the carbon cycle. A variety of techniques for mapping forest height using remote sensing data have been successfully developed in recent years. However, the demands for forest height mapping in practical applications are often not met, due to the lack of corresponding remote sensing data. In such cases, it would be useful to exploit the latest, cheaper datasets and combine them with free datasets for the mapping of forest canopy height. In this study, we proposed a method that combined ZiYuan-3 (ZY-3) stereo images, Shuttle Radar Topography Mission global 1 arc second data (SRTMGL1), and Landsat 8 Operational Land Imager (OLI) surface reflectance data. The method consisted of three procedures: First, we extracted a digital surface model (DSM) from the ZY-3, using photogrammetry methods and subtracted the SRTMGL1 to obtain a crude canopy height model (CHM). Second, we refined the crude CHM and correlated it with the topographically corrected Landsat 8 surface reflectance data, the vegetation indices, and the forest types through a Random Forest model. Third, we extrapolated the model to the entire study area covered by the Landsat data, and obtained a wall-to-wall forest canopy height product with 30 m × 30 m spatial resolution. The performance of the model was evaluated by the Random Forest’s out-of-bag estimation, which yielded a coefficient of determination (R2) of 0.53 and a root mean square error (RMSE) of 3.28 m. We validated the predicted forest canopy height using the mean forest height measured in the field survey plots. The validation result showed an R2 of 0.62 and a RMSE of 2.64 m.

Biodegradation of low molecular weight organic acids in rhizosphere soils from a tropical montane rain forest