Modeling of Environmental Impacts on Aerial Hyperspectral Images for Corn Plant Phenotyping

Aerial imaging technologies have been widely applied in agricultural plant remote sensing. However, an as yet unexplored challenge with field imaging is that the environmental conditions, such as sun angle, cloud coverage, temperature, and so on, can significantly alter plant appearance and thus affect the imaging sensor’s accuracy toward extracting plant feature measurements. These image alterations result from the complicated interaction between the real-time environments and plants. Analysis of these impacts requires continuous monitoring of the changes through various environmental conditions, which has been difficult with current aerial remote sensing systems. This paper aimed to propose a modeling method to comprehensively understand and model the environmental influences on hyperspectral imaging data. In 2019, a fixed hyperspectral imaging gantry was constructed in Purdue University’s research farm, and over 8000 repetitive images of the same corn field were taken with a 2.5 min interval for 31 days. Time-tagged local environment data, including solar zenith angle, solar irradiation, temperature, wind speed, and so on, were also recorded during the imaging time. The images were processed for phenotyping data, and the time series decomposition method was applied to extract the phenotyping data variation caused by the changing environments. An artificial neural network (ANN) was then built to model the relationship between the phenotyping data variation and environmental changes. The ANN model was able to accurately predict the environmental effects in remote sensing results, and thus could be used to effectively eliminate the environment-induced variation in the phenotyping features. The test of the normalized difference vegetation index (NDVI) calculated from the hyperspectral images showed that variance in NDVI was reduced by 79%. A similar performance was confirmed with the relative water content (RWC) predictions. Therefore, this modeling method shows great potential for application in aerial remote sensing applications in agriculture, to significantly improve the imaging quality by effectively eliminating the effects from the changing environmental conditions.

Studi Bahaya Antropogenik yang Disebabkan Pembuangan Sampah di Bentuklahan Fluvio-Marin di Sebagian Muara Angke, Jakarta Menggunakan Data Penginderaan Jauh Udara

Anthropogenic hazards are hazards arising from human actions or negligences. Anthropogenic hazards can affect both human and the broader ecosystem and various landforms. Waste as the effect of human activity is a big problem in urban areas related to the difficulty of waste management while waste production continues to increase. The impact of poor waste management in the city is a potential anthropogenic hazard for the region. Part of the city that often receives less attention related to waste or environmental sanitation and has been negatively affected by waste is the coastal area in a big city, which is kind of fluvio-marine landform unit, one of which is Muara Angke, which is the study area of this research. Identification of the waste disposal site is carried out to determine the level of anthropogenic hazard posed by waste in the area. With very high spatial resolution obtained by aerial remote sensing data, identification of objects in urban areas such as waste disposal site can be conducted. The purpose of this study is to identify the waste disposal site in part of Muara Angke region and to identify the potential of anthropogenic hazard caused by waste in the area. The data used is the LSU (LAPAN Surveillance UAV) camera data. The method proposed in this research is visual interpretation LSU camera data. The result showed that waste disposal location can be performed using aerial remote sensing data and visual interpretation to the data.

Remote Sensing for Detection of Ganoderma Disease and Bagworm Infestation in Oil Palm

Two major disease and pest in oil palm are Ganoderma disease and bagworm infestation. Ganoderma disease caused by Ganoderma boninense and bagworm infestation caused by Metisa Plana has caused significant loss to oil palm industry. Therefore, early detection and control are important to reduce the losses. This paper reviewed the existing approaches, challenges and future trend of aerial remote sensing technology for Ganoderma disease and bagworm infestation in oil palm. The aerial remote sensing technology comprises of multispectral, hyperspectral camera and radar which have different platform such as satellite, aircraft and Unmanned Aerial Vehicle (UAV). The aerial multispectral and hyperspectral remote sensing analysed spectral signatures from visible and near infrared spectrum range for detection of the disease and pest attacks. Studies showed that satellite-based multispectral remote sensing only provide moderate accuracy (<70%) compared to UAV-based multispectral remote sensing (>80%) for detection of disease and pest infestation. Meanwhile, our study using UAV showed 90% of accuracy for moderate and severe Ganoderma disease detection in oil palm. Meanwhile, application of aerial hyperspectral remote sensing for Ganoderma disease showed potential for early detection of Ganoderma disease in oil palm and also can be used to detect early pest infestation in oil palm based on field spectroscopy results. Other than that, radar remote sensing has also able to differentiate healthy and Ganoderma-infected oil palm and also pest infestation by analysis of radar backscatter image of the foliar, frond and crown of oil palm. The challenges for the implementation of aerial remote sensing technology for disease and pest detection in oil palm is in tackling problems from shadows, mixed-class from single canopy and false-positive classification and also producing equipment at a lower and affordable price and also a user-friendly data analysis system that can be used by the plantations for a fast disease and pest detection works. The introduction of Artificial Intelligence (AI), Machine Deep Learning (MDL), low-cost remote sensing camera and light-weight UAV has opened the opportunity to tackle the challenges. As a conclusion, aerial remote sensing provides better and faster disease and pest infestation detection system compared to ground-based inspection. The advancement of the aerial remote sensing technology can provide more economic and efficient disease and pest infestation detection system for large oil palm plantation areas.