We investigated the capabilities of a canopy height model (CHM) derived from aerial photographs using the Structure from Motion (SfM) approach to estimate aboveground biomass (AGB) in a tropical forest. Aerial photographs and airborne Light Detection and Ranging (LiDAR) data were simultaneously acquired under leaf-on canopy conditions. A 3D point cloud was generated from aerial photographs using the SfM approach and converted to a digital surface model (DSM_P). We also created a DSM from airborne LiDAR data (DSM_L). From each of DSM_P and DSM_L, we constructed digital terrain models (DTM), which are DTM_P and DTM_L, respectively. We created four CHMs, which were calculated from (1) DSM_P and DTM_P (CHM_PP); (2) DSM_P and DTM_L (CHM_PL); (3) DSM_L and DTM_P (CHM_LP); and (4) DSM_L and DTM_L (CHM_LL). Then, we estimated AGB using these CHMs. The model using CHM_LL yielded the highest accuracy in four CHMs (R² = 0.94) and was comparable to the model using CHM_PL (R² = 0.93). The model using CHM_PP yielded the lowest accuracy (R² = 0.79). In conclusion, AGB can be estimated from CHM derived from aerial photographs using the SfM approach in the tropics. However, to accurately estimate AGB, we need a more accurate DTM than the DTM derived from aerial photographs using the SfM approach.

The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6% for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3%) or Sentinel-1 (75.5%). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.

In 2016, in response to forest loss, the Myanmar government banned logging operations for 1 year throughout the entire country and for 10 years in specific regions. However, it is unclear whether this measure will effectively reduce forest loss, because disturbance agents other than logging may have substantial effects on forest loss. In this study, we investigated an approach to attribute disturbance agents to forest loss, and we characterized the attribution of disturbance agents, as well as the areas affected by these agents, in tropical seasonal forests in the Bago Mountains, Myanmar. A trajectory-based analysis using a Landsat time series was performed to detect change pixels. After the aggregation process that grouped adjacent change pixels in the same year as patches, a change attribution was implemented using the spectral, geometric, and topographic information of each patch via random forest modeling. The attributed agents of change include “logging”, “plantation”, “shifting cultivation”, “urban expansion”, “water invasion”, “recovery”, “other change”, and “no change”. The overall accuracy of the attribution model at the patch and area levels was 84.7% and 96.0%, respectively. The estimated disturbance area from the attribution model accounted for 10.0% of the study area. The largest disturbance agent was found to be logging (59.8%), followed by water invasion (14.6%). This approach quantifies disturbance agents at both spatial and temporal scales in tropical seasonal forests, where limited information is available for forest management, thereby providing crucial information for assessing forest conditions in such environments.

Accurately mapping land use/land cover changes (LULCC) and forest disturbances provides valuable information for understanding the influence of anthropogenic activities on the environment at regional and global scales. Many approaches using satellite remote sensing data have been proposed for characterizing these long-term changes. However, a spatially and temporally consistent mapping of both LULCC and forest disturbances at medium spatial resolution is still limited despite their critical contributions to the carbon cycle. In this study, we examined the applicability of Landsat time series temporal segmentation and random forest classifiers to mapping LULCC and forest disturbances in Vietnam. We used the LandTrendr temporal segmentation algorithm to derive key features of land use/land cover transitions and forest disturbances from annual Landsat time series data. We developed separate random forest models for classifying land use/land cover and detecting forest disturbances at each segment and then derived LULCC and forest disturbances that coincided with each other during the period of 1988–2019. The results showed that both LULCC classification and forest disturbance detection achieved low accuracy in several classes (e.g., producer’s and user’s accuracies of 23.7% and 78.8%, respectively, for forest disturbance class); however, the level of accuracy was comparable to that of existing datasets using the same reference samples in the study area. We found relatively high confusion between several land use/land cover classes (e.g., grass/shrub, forest, and cropland) that can explain the lower overall accuracies of 67.6% and 68.4% in 1988 and 2019, respectively. The mapping of forest disturbances and LULCC suggested that most forest disturbances were followed by forest recovery, not by transitions to other land use/land cover classes. The landscape complexity and ephemeral forest disturbances contributed to the lower classification and detection accuracies in this study area. Nevertheless, temporal segmentation and derived features from LandTrendr were useful for the consistent mapping of LULCC and forest disturbances. We recommend that future studies focus on improving the accuracy of forest disturbance detection, especially in areas with subtle landscape changes, as well as land use/land cover classification in ambiguous and complex landscapes. Using more training samples and effective variables would potentially improve the classification and detection accuracies.

Forest disturbances are generally estimated using globally available forest change maps or locally calibrated disturbance maps. The choice of disturbance map depends on the trade-offs among the detection accuracy, processing time, and expert knowledge. However, the accuracy differences between global and local maps have still not been fully investigated; therefore, their optimal use for estimating forest disturbances has not been clarified. This study assesses the annual forest disturbance detection of an available Global Forest Change map and a local disturbance map based on a Landsat temporal segmentation algorithm in areas dominated by harvest disturbances. We assess the forest disturbance detection accuracies based on two reference datasets in each year. We also use a polygon-based assessment to investigate the thematic accuracy based on each disturbance patch. As a result, we found that the producer’s and user’s accuracies of disturbances in the Global Forest Change map were 30.1–76.8% and 50.5–90.2%, respectively, for 2001–2017, which corresponded to 78.3–92.5% and 88.8–97.1%, respectively in the local disturbance map. These values indicate that the local disturbance map achieved more stable and higher accuracies. The polygon-based assessment showed that larger disturbances were likely to be accurately detected in both maps; however, more small-scale disturbances were at least partially detected by the Global Forest Change map with a higher commission error. Overall, the local disturbance map had higher forest disturbance detection accuracies. However, for forest disturbances larger than 3 ha, the Global Forest Change map achieved comparable accuracies. In conclusion, the Global Forest Change map can be used to detect larger forest disturbances, but it should be used cautiously because of the substantial commission error for small-scale disturbances and yearly variations in estimated areas and accuracies.