Search

[Display omitted] The precise estimation of the number of trees, their individual tree locations, along with species information, is crucial for enhancing ecosystem services in urban areas. Previous studies largely used satellite or airborne images for mapping trees, but they were insufficient to generate a large number of species distributions. Ground-level data also led to inaccurate positional information of individual trees, although they provided reliable species detection results. In this study, we propose a novel framework that fully explores the complementary strengths of air- and ground-level sensing platforms by leveraging various deep neural networks to generate a detailed tree maps at a city-wide scale. Our strategy includes individual tree mapping and tree species detection using three-color channel images acquired from multiple sensing platforms. Through publicly available airborne imagery, we estimate the presence of over 1.2 million trees in Suwon city of South Korea spanning 121.04 km2 (R2 of 0.95 and relative bias of −1.9 %), achieving more accurate individual tree positions (positional uncertainty around 2.0 m) than conventional methods. Our comprehensive experiments also demonstrate the effectiveness of utilizing tree bark photos and street-level imagery taken by citizens and vehicles to identify urban tree species, with accuracy rates of over 80 % for citizen-sensed tree species maps and 66 % for vehicle-sensed tree species map. Along with the proliferation of web-based airborne images, the widespread use of smartphones, and the advancements in vehicle-mounted sensors, this study can facilitate efficient and accurate management of urban trees across scales. For reproducibility of the study, we share the source code and datasets at https://github.com/landkwon94/ryoungseob-master. [ABSTRACT FROM AUTHOR]

[Display omitted] Detailed spatial representations of terrestrial vegetation are essential for precision agricultural applications and the monitoring of land cover changes in heterogeneous landscapes. The advent of satellite-based remote sensing has facilitated daily observations of the Earth's surface with high spatial resolution. In particular, a data fusion product such as Planet Fusion has realized the delivery of daily, gap-free surface reflectance data with 3-m pixel resolution through full utilization of relatively recent (i.e., 2018-) CubeSat constellation data. However, the spatial resolution of past satellite sensors (i.e., 30–60 m for Landsat) has restricted the detailed spatial analysis of past changes in vegetation. In order to overcome the spatial resolution constraint of Landsat data for long-term vegetation monitoring, we propose a dual remote-sensing super-resolution generative adversarial network (dual RSS-GAN) approach combining Planet Fusion and Landsat 8 data to simulate spatially enhanced long-term time-series of the normalized difference vegetation index (NDVI) and near-infrared reflectance from vegetation (NIRv). We evaluated the performance of the dual RSS-GAN against in situ tower-based continuous measurements (up to 8 years) and remotely piloted aerial system-based maps of cropland and deciduous forest in the Republic of Korea. The dual RSS-GAN enhanced spatial representations in Landsat 8 images and captured seasonal variation in vegetation indices (R2 > 0.90, for the dual RSS-GAN maps vs in situ data from all sites). Overall, the dual RSS-GAN reduced Landsat 8 vegetation index underestimations compared with in situ measurements; relative bias values of NDVI ranged from − 5.8 % to 0.3 % and − 12.4 % to − 3.7 % for the dual RSS-GAN and Landsat 8, respectively. This improvement was caused by spatial enhancement through the dual RSS-GAN, which reflects fine-scale information from Planet Fusion. Finally, the dual RSS-GAN maps showed both spatial enhancement and reducing the underestimation of vegetation index in historic Landsat dataset from 1984. This study presents a new approach for resolving sub-pixel spatial information in Landsat images. [ABSTRACT FROM AUTHOR]

Ground reference data are an essential prerequisite for supervised crop mapping. The lack of a low-cost and efficient ground referencing method results in pervasively limited reference data and hinders crop classification. In this study, we apply a convolutional neural network (CNN) model to explore the efficacy of automatic ground truthing via Google Street View (GSV) images in two distinct farming regions: Illinois and the Central Valley in California. We demonstrate the feasibility and reliability of our new ground referencing technique by performing pixel-based crop mapping at the state level using the cloud-based Google Earth Engine platform. The mapping results are evaluated using the United States Department of Agriculture (USDA) crop data layer (CDL) products. From ~ 130,000 GSV images, the CNN model identified ~ 9,400 target crop images. These images are well classified into crop types, including alfalfa, almond, corn, cotton, grape, rice, soybean, and pistachio. The overall GSV image classification accuracy is 92% for the Central Valley and 97% for Illinois. Subsequently, we shifted the image geographical coordinates 2–3 times in a certain direction to produce 31,829 crop reference points: 17,358 in Illinois, and 14,471 in the Central Valley. Evaluation of the mapping results with CDL products revealed satisfactory coherence. GSV-derived mapping results capture the general pattern of crop type distributions for 2011–2019. The overall agreement between CDL products and our mapping results is indicated by R2 values of 0.44–0.99 for the Central Valley and 0.81–0.98 for Illinois. To show the applicational value of the proposed method in other countries, we further mapped rice paddy (2014–2018) in South Korea which yielded fairly well outcomes (R2 = 0.91). These results indicate that GSV images used with a deep learning model offer an efficient and cost-effective alternative method for ground referencing, in many regions of the world. [ABSTRACT FROM AUTHOR]

Himawari-8, a new-generation geostationary satellite, can retrieve sub-hourly land surface temperatures (LSTs) with moderate spatial resolution, providing a new scale for monitoring the thermal environment in Asia and Oceania. This study evaluated uncertainties of LSTs retrieved by three operational algorithms from Advanced Himawari Imager (AHI) data. We compared two nonlinear split-window algorithms (SOB and WAN algorithms) and one nonlinear three-band algorithm (YAM algorithm). First, the error characteristics of the retrieved LSTs caused by the input parameter errors were simulated under various land-atmospheric conditions using an atmospheric radiative transfer model. Thereafter, retrieved LSTs from actual AHI data were evaluated using in-situ observations from AsiaFlux and OzFlux networks and the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) LSTs. The simulated results showed that the YAM algorithm maintained the highest accuracy, whereas the WAN algorithm had the highest robustness to input errors. The YAM algorithm had the smallest total error including input errors over a wide range of retrieval conditions. Validation of the three algorithms via in-situ LSTs from 12 sites revealed nighttime mean RMSEs for all sites of ∼1.7 °C, and daytime mean RMSEs for semi-arid and humid sites of approximately 3.0 °C and 2.0 °C, respectively. These are comparable to the accuracies reported for LST products with higher spatial resolutions, such as the Moderate Resolution Imaging Spectroradiometer and Landsat. Within the Himawari-8 disk, the estimation error of the YAM algorithm was ∼1.0 °C lower than those of the SOB and WAN algorithms in regions with extremely high viewing angle, temperature, and humidity (e.g., northern China, Australia, and Southeast Asia). Furthermore, AHI LSTs showed closer agreement with ECOSTRESS compared to in-situ LSTs, suggesting the usefulness of ECOSTRESS for assessing the diurnal LSTs derived from geostationary satellites. The resulting LST products and the knowledge of their error characteristics have the potential to improve the collective understanding of terrestrial energy and water cycles based on improved accuracy and robustness. [ABSTRACT FROM AUTHOR]