Sunday, August 18, 2024

Transforming satellite imagery: innovative fusion method for precision agriculture

Journal of Remote Sensing

image:
Flowchart of StarFusion.
view more
Credit: Journal of Remote Sensing

Researchers have introduced StarFusion, a cutting-edge spatiotemporal fusion method that significantly improves the temporal resolution and fusion accuracy of high-resolution satellite imagery in agriculture. By fusing data from China's Gaofen-1 and Europe's Sentinel-2 satellites, StarFusion addresses the common problem of infrequent imaging due to long revisit periods and cloud cover interference from high-resolution satellites, which often hinders the effectiveness of high-resolution remote sensing in dynamic agricultural environments. By integrating deep learning with traditional regression models, the method enhances both spatial detail and temporal resolution, making it an invaluable tool for more effective crop monitoring and management.

Remote sensing plays a vital role in monitoring agricultural landscapes, yet current satellite sensors often struggle with the trade-off between spatial and temporal resolution. High spatial resolution images, while detailed, are often limited by infrequent captures and cloud interference, reducing their utility in rapidly changing environments. Conversely, images with better temporal resolution lack the necessary spatial detail for precise analysis. These challenges underscore the need for advanced fusion methods that can better serve agricultural applications.

A team from the State Key Laboratory of Remote Sensing Science at Beijing Normal University, in collaboration with other institutions, has developed StarFusion, a new spatiotemporal fusion method. Published (DOI: 10.34133/remotesensing.0159) on July 22, 2024, in the Journal of Remote Sensing, the study combines deep learning and traditional regression techniques to address the limitations of current fusion methods. StarFusion effectively merges high-resolution Gaofen-1 data with medium-resolution Sentinel-2 data, resulting in significantly enhanced imagery for agricultural monitoring.

StarFusion represents an innovative approach to spatiotemporal image fusion, blending the strengths of deep learning and traditional regression models. By integrating a super-resolution generative adversarial network (SRGAN) with a partial least squares regression (PLSR) model, StarFusion achieves high fusion accuracy while preserving fine spatial details. The method effectively manages challenges like spatial heterogeneity and limited cloud-free image availability, making it highly practical for real-world agricultural applications. Extensive testing across various agricultural sites has shown that StarFusion outperforms existing techniques, particularly in maintaining spatial detail and enhancing temporal resolution. Its capability to function with minimal cloud-free data sets it apart, providing a reliable solution for crop monitoring in regions plagued by frequent cloud cover.

"StarFusion represents an valuable attempt in remote sensing technology for agriculture," said Professor Jin Chen, the study's lead author. "Its ability to generate high-quality images with improved temporal resolution will greatly enhance precision agriculture and environmental monitoring."

StarFusion offers significant advantages for digital agriculture, providing high-resolution imagery essential for detailed crop monitoring, yield prediction, and disaster assessment. Its ability to produce accurate images despite cloud cover and limited data availability makes it particularly valuable for agricultural management in regions with challenging weather conditions. As this technology evolves, StarFusion is expected to play a crucial role in advancing agricultural productivity and sustainability.

###

References

DOI

10.34133/remotesensing.0159

Original Source URL

https://spj.science.org/doi/10.34133/remotesensing.0159

Funding information

This study was supported by High-Resolution Earth Observation System (09-Y30F01-9001-20/22).

About Journal of Remote Sensing

The Journal of Remote Sensing, an online-only Open Access journal published in association with AIR-CAS, promotes the theory, science, and technology of remote sensing, as well as interdisciplinary research within earth and information science.

Journal

Journal of Remote Sensing

DOI

10.34133/remotesensing.0159

Subject of Research

Not applicable

Article Title

A Hybrid Spatiotemporal Fusion Method for High Spatial Resolution Imagery: Fusion of Gaofen-1 and Sentinel-2 over Agricultural Landscapes

PolyU researchers invent intelligent soft robotic clothing for automatic thermal adaptation in extreme heat

The Hong Kong Polytechnic University

As global warming intensifies, people increasingly suffer from extreme heat. For those working in a high-temperature environment indoors or outdoors, keeping thermally comfortable becomes particularly crucial. A team led by Dr Dahua SHOU, Limin Endowed Young Scholar in Advanced Textiles Technologies and Associate Professor of the School of Fashion and Textiles of The Hong Kong Polytechnic University (PolyU) has developed first-of-its-kind thermally-insulated and breathable soft robotic clothing that can automatically adapt to changing ambient temperatures, thereby helping to ensure worker safety in hot environments. Their research findings have been published in the international interdisciplinary journal Advanced Science.

Maintaining a constant body temperature is one of the most critical requirements for living and working. High-temperature environments elevate energy consumption, leading to increased heat stress, thus exacerbating chronic conditions such as cardiovascular disease, diabetes, mental health issues and asthma, while also increasing the risk of infectious disease transmission. According to the World Health Organisation, globally, there were approximately 489,000 heat-related deaths annually between 2000 and 2019, with 45% occurring in Asia and 36% in Europe.

Thermal protective clothing is essential to safeguard individuals in extreme high-temperature environments, such as firefighters who need to be present at fires scenes and construction workers who work outdoors for extended periods. However, traditional gear has been limited by statically fixed thermal resistance, which can lead to overheating and discomfort in moderate conditions, while its heat insulation may not offer sufficient protection in extreme fire events and other high-temperature environments. To address this issue, Dr Shou and his team have developed intelligent soft robotic clothing for automatic temperature adaptation and thermal insulation in hot environments, offering superior personal protection and thermal comfort across a range of temperatures.

Their research was inspired by biomimicry in nature, like the adaptive thermal regulation mechanism in pigeons, which is mainly based on structural changes. Pigeons use their feathers to trap a layer of air surrounding their skin to reduce heat loss to the environment. When the temperature drops, they fluff up their feathers to trap a significant amount of still air, thereby increasing thermal resistance and retaining warmth.

The protective clothing developed by the team uses soft robotic textile for dynamic adaptive thermal management. Soft actuators, designed like a human network-patterned exoskeleton and encapsulating a non-toxic, non-flammable, low-boiling-point fluid, were strategically embedded within the clothing. This thermo-stimulated system turns the fluid from a liquid into a gas when the ambient temperature rises, causing expansion of soft actuators and thickening the textile matrix, thereby enhancing the gap of still air and doubling the thermal resistance from 0.23 to 0.48 Km²/W. The protective clothing can also keep the inner surface temperatures at least 10°C cooler than conventional heat-resistant clothing, even when the outer surface reaches 120°C.

This unique soft robotic textile, made by thermoplastic polyurethane, is soft, resilient and durable. Notably, it is far more skin-friendly and conformable than temperature-responsive clothing embedded with shape-memory alloys and is adjustable for a wide range of protective clothing. The soft actuators have exhibited no signs of leakage after undergoing rigorous standard washing tests. The porous, spaced knitting structure of the material can also significantly reduce convective heat transfer while maintaining high moisture breathability. Not relying on thermoelectric chips or circulatory liquid cooling systems for cooling or heat conduction, the light-weighted, soft robotic clothing can effectively regulate temperature itself without any energy consumption.

Dr Shou said, “Wearing heavy firefighting gear can feel extremely stifling. When firefighters exit a fire scene and remove their gear, they are sometimes drained nearly a pound of sweat from their boots. This has motivated me to develop a novel suit capable of adapting to various environmental temperatures while maintaining excellent breathability. Our soft robotic clothing can seamlessly adapt to different seasons and climates, multiple working and living conditions, and transitions between indoor and outdoor environments to help users experience constant thermal comfort under intense heat.”

Looking forward, Dr Shou finds the innovation to have a wide range of potential applications, from activewear, winter jackets, healthcare apparel and outdoor gear, to sustainable textile-based insulation for construction and buildings, contributing to energy-saving efforts. Supported by the Innovation and Technology Commission and the Hong Kong Research Institute of Textiles and Apparel, Dr Shou and his team have also extended the thermo-adaptive concept to develop inflatable, breathable jackets and warm clothing. This soft robotic clothing is suitable for low-temperature environments or sudden temperature drops to aid those who are stranded in the wilderness to maintain normal body temperature.

Design concept of thermally adaptive soft robotic textiles. a) Under normal conditions, the SRT's slim profile and reduced thermal resistance facilitate the transfer of heat and moisture away from the skin. b) Upon exposure to a fire environment, the SRT activates to provide enhanced thermal protection maintaining lightness and breathability. Specifically, outside fire events, SRT layers deflate for low thermal resistance; when activated in a fire scenario, the layers separate, creating an insulating air gap that impedes heat transfer. c) Illustration of the SRT featuring a flame-resistant outer layer, a breathable moisture barrier, a knitted thermal liner, and an STA filled with a low boiling point fluid. d) Construction specifics of the knitted thermal liner with embedded STAs. e) Phase transition of a low boiling point fluid within the STA, characterized by significant volume change: in ambient temperatures, the fluid remains in a liquid state; as temperatures rise, the fluid vaporizes, and then reverts into a liquid upon cooling.

Experimental and Simulated Results of Thermal Analysis. a) Configuration of the radiant heat exposure test setup. b) Inner layer temperature profiles of traditional textiles (TT) and SRT under radiant heat. c) Duration required for reaching threshold temperatures of 44 and 56 °C, and the ultimate temperature attained during radiant heat exposure (Note: t56 = 700 s indicates the test duration to attain 56 °C). d) Simulated temperature and airflow velocity distribution in SRT subjected to radiant heat. e) Illustration of the hot surface contact test apparatus. f) Inner layer temperature profiles of TT and SRT during direct contact with a heated surface. g) Variations of time required to reach 44 and 56 °C upon contact with a hot surface. h) Simulation of temperature and airflow velocity distribution in SRT during hot surface contact. i) Set-up for evaluating thermal and moisture resistance properties. j) Comparison of thermal resistance of TT, SRT in a deflated state, and SRT in an inflated state. k) Comparison of moisture resistance of TT, SRT in a deflated state, and SRT in an inflated state. l) Comparison of thickness for TT, SRT in a deflated state, and SRT in an inflated state.

Thermoadaptation of STA embedded in a customized knitted fabric. a,b) Illustrations of the knitted thermal liner (240 mm × 340 mm) featuring a connecting clasp (width:15 mm) and a channel (width:60 mm) for STA. c) The STA within the knitted thermal liner depicted in a fully deflated state, exhibiting minimal thickness. d) The STA encapsulated in the knitted thermal liner shown in a fully inflated state, achieving maximal thickness. e) Comparison of thermal and moisture resistance between traditional liners and present SRTs. f) Cross-sectional views of the SRT in the fully deflated and fully inflated states. g) Images of the SRT in its initial, inactive state progressing to the fully activated state. h) Schematic representation of an SRT-based firefighter garment exposed to radiant heat. i) Side view of the garment in its initial state. j) Side view of the garment once thermally activated.

Credit