Assessment of Differential Forest Growth Following Disturbance in Minnesota, USA

We used LiDAR metrics and satellite imagery to examine regeneration on forested sites disturbed via harvest or natural means over a 44-year period. We tested the effectiveness of older low-density LiDAR elevation data in producing information related to existing levels of above ground biomass (AGB). To accomplish this, we paired the elevation data with a time series of wetness and greenness indices derived from Landsat satellite imagery to model changes in AGB for sites experiencing different agents of change. Current AGB was determined from high-density LiDAR acquired in northern Minnesota, USA. We then compared high-density LiDAR-based AGB and estimates modeled using Landsat and low-density LiDAR indices for 10,068 sites. Clear differences were found in standing AGB and accumulation rates between sites disturbed by different agents of change. Biomass accumulation following disturbance appears to decrease rapidly following an initial spike as stands 1asZX respond to newly opened growing space. Harvested sites experienced a roughly six-fold increase in the rate of biomass accumulation compared to sites subjected to stand replacing fire or insect and disease, and a 20% increase in productivity when compared to sites subjected to wind mediated canopy loss. Over time, this resulted in clear differences in standing AGB.

A Large-Scale Dataset and Deep Learning Model for Detecting and Counting Olive Trees in Satellite Imagery

Since the Pre-Roman era, olive trees have a significant economic and cultural value. In 2019, the Al-Jouf region, in the north of the Kingdom of Saudi Arabia, gained a global presence by entering the Guinness World Records, with the largest number of olive trees in the world. Olive tree detecting and counting from a given satellite image are a significant and difficult computer vision problem. Because olive farms are spread out over a large area, manually counting the trees is impossible. Moreover, accurate automatic detection and counting of olive trees in satellite images have many challenges such as scale variations, weather changes, perspective distortions, and orientation changes. Another problem is the lack of a standard database of olive trees available for deep learning applications. To address these problems, we first build a large-scale olive dataset dedicated to deep learning research and applications. The dataset consists of 230 RGB images collected over the territory of Al-Jouf, KSA. We then propose an efficient deep learning model (SwinTUnet) for detecting and counting olive trees from satellite imagery. The proposed SwinTUnet is a Unet-like network which consists of an encoder, a decoder, and skip connections. Swin Transformer block is the fundamental unit of SwinTUnet to learn local and global semantic information. The results of an experimental study on the proposed dataset show that the SwinTUnet model outperforms the related studies in terms of overall detection with a 0.94% estimation error.

Mapping Large-Scale Plateau Forest in Sanjiangyuan Using High-Resolution Satellite Imagery and Few-Shot Learning

Monitoring the extent of plateau forests has drawn much attention from governments given the fact that the plateau forests play a key role in global carbon circulation. Despite the recent advances in the remote-sensing applications of satellite imagery over large regions, accurate mapping of plateau forest remains challenging due to limited ground truth information and high uncertainties in their spatial distribution. In this paper, we aim to generate a better segmentation map for plateau forests using high-resolution satellite imagery with limited ground-truth data. We present the first 2 m spatial resolution large-scale plateau forest dataset of Sanjiangyuan National Nature Reserve, including 38,708 plateau forest imagery samples and 1187 handmade accurate plateau forest ground truth masks. We then propose an few-shot learning method for mapping plateau forests. The proposed method is conducted in two stages, including unsupervised feature extraction by leveraging domain knowledge, and model fine-tuning using limited ground truth data. The proposed few-shot learning method reached an F1-score of 84.23%, and outperformed the state-of-the-art object segmentation methods. The result proves the proposed few-shot learning model could help large-scale plateau forest monitoring. The dataset proposed in this paper will soon be available online for the public.

The Orientation of the Kofun Tombs

The Kofun period of the history of Japan—between the 3rd and the 7th century AD—bears its name from the construction of huge, earth mound tombs called Kofun. Among them, the largest have a keyhole shape and are attributed to the first, semi-legendary emperors. The study of the orientation of ancient tombs is usually a powerful tool to better understand the cognitive aspects of religion and power in ancient societies. This study has never been carried out in Japan due to the very large number of Kofun and to the fact that access to the perimeter is usually forbidden. For these reasons, to investigate Kofun orientations, simple tools of satellite imagery are used here. Our results strongly point to a connection of all Kofun entrance corridors with the arc of the sky where the Sun and the Moon are visible every day of the year; additionally, these show an orientation of the keyhole Kofun to the arc of the rising/shining Sun, the goddess that the Japanese emperors put at the mythical origin of their dynasty.