Machine Learning-Enabled Inverse Design of Radiative Cooling Film with On-Demand Transmissive Color

Abstract

Passive radiative cooling is a cost-efficient and eco-friendly approach to cool terrestrial objects by dissipating heat to the outer space. Colored radiative cooling (CRC) has many advantages over conventional passive radiative cooling and has garnered growing interest recently. However, existing CRC films are normally opaque, where the incident sunlight is either reflected for rendering color or absorbed to generate waste heat. In this work, we design a transmissive CRC film that allows a specific portion of light to pass through and provides more vivid colors. Such a transmissive film achieves the coloration and cooling dual-function by stacking a solar transparent selective emitter on top of a nanocavity-based color filter. The top emitter is first designed by using a mixed-integer memetic algorithm, where the layer materials, their number sequence, and thicknesses are simultaneously optimized. The variability in both material composition and layer thickness enables the emitter with a near-ideal emissivity in the atmospheric windows for subambient cooling, and an ultrahigh transmissivity in the solar range for sunlight penetration. Then, the structures of bottom nanocavity are determined by using a tandem neural network for on-demand color generation. This machine learning-assisted inverse design approach provides real-time structure prediction for on-demand colors and offers great flexibility in balancing the cooling and coloring functionalities. The proposed methodology can have special significance in broadening the application of passive radiative coolers in energy-efficient buildings, power-generating windows, and sustainable greenhouses.

Optimization of Dielectric-Metal Multilayer Structure for Color-Preserving Radiative Cooling Window

“…As depicted in Figure a,b, an ideal CPRCW should satisfy a flat transmittance curve in the visible band, a reflectance of 1 in the near-infrared band, and an emittance of 1 in the atmospheric window. Given that these multispectral characteristics are closely coupled, minor modifications in structure or material composition can influence transmissivity, reflectance, and emissivity, impacting cooling efficiency and visibility . Thus, designing multilayer films to simultaneously achieve high visible transmittance, high near-infrared reflectance, and high middle-infrared emittance is challenging due to these factors.…”

“…This configuration cleverly separates the color-preserving TNR and the thermal emitter, as shown in Figure d: (i) the lower TNR has uniformly flat transmittance in visible wavelength, blocking incoming NIR solar radiation; (ii) the upper PDMS serves as the thermal emitter, continuously releasing heat into space through atmospheric windows for radiative cooling. In the field of radiative cooling, there are many other papers that have also employed this method. ,, By combination of TNR with the thermal emitter (PDMS), the concept of radiative cooling windows has emerged. Due to the minimal impact on each other, the designs for the lower TNR and the upper emitter can be optimized one after the other.…”

“…This approach is increasingly recognized for its potential to cut energy use, reduce CO 2 emissions, and mitigate the greenhouse effect. ,− For effective radiative cooling, a device should exhibit high emissivity in the atmospheric window (8–13 μm) and high reflectivity within the solar radiation range. , When the cooler exhibits high transmittance within the visible light spectrum, high reflectance in the NIR band, and high emittance through the atmospheric window, it qualifies as a transparent radiative cooler. For example, in 2023, Guan et al theoretically designed and optimized a transmissive colored radiative cooling film that allows a specific portion of light to pass through and provides more vivid colors by means of a mixed-integer memetic algorithm and machine learning. In 2024, Li et al theoretically proposed an adaptive radiative cooling system based on W–VO 2 , where the spectra at high and low temperatures can be easily adjusted by varying the thickness of each layer and the ratio of W–VO 2 .…”

“…In 2024, Li et al theoretically proposed an adaptive radiative cooling system based on W–VO 2 , where the spectra at high and low temperatures can be easily adjusted by varying the thickness of each layer and the ratio of W–VO 2 . Currently, such cooling techniques are employed in solar cells, thermoelectric generator cooling, triboelectric nanogenerator, − thermoelectric power generator, radiative coolers that modulate color, ,,, transparent radiative cooling window, ,, and so on.…”

Spectral Emissivity Profiles for Radiative Cooling

“…These material systems are enabled by advancements in computational design, fabrication, and characterization tools of optical structures. − Multilayers, micro/nanoparticle-embedded polymeric coatings, and polymers with artificially engineered porosities are among some of the structures that are utilized for radiative cooling purposes. Layered structures which consist of a combination of different materials are one of the simplest, yet very effective, ways of realizing the desired emissivity profile for radiative cooling. ,− Usually, materials with strong absorption in the 8–13 μm wavelength range and near-lossless in the visible and near-infrared spectra, such as SiO 2 , Al 2 O 3 , TiO 2 , HfO 2 , are used together with a metal which provides broadband reflection. Tailoring of the interference of the propagating wave components inside the structure is the fundamental mechanism that leads to target spectral characteristics.…”