Dual-UAV system boosts color accuracy in crop remote sensing

Nanjing Agricultural University The Academy of Science

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Tests showed that this method improved color fidelity by over 70%, aligning image color with ground-truth measurements and enhancing rice maturity prediction accuracy from R² = 0.28 to 0.67. The technology offers a scalable pathway for reliable high-throughput phenotyping and breeding applications in precision agriculture.

Plant color reflects physiological status, nutrient levels, and biotic or abiotic stress, making it a key trait in breeding and field management. Traditional visual inspection is subjective and inefficient, while satellite imagery lacks resolution for fine phenotyping. UAV-based remote sensing fills this gap, but outdoor imaging suffers from inconsistent illumination, camera variability, and flight-to-flight differences. Past solutions—image feature transfer, reference image selection, deep learning enhancement—improved color consistency to some extent, but accuracy was limited and performance depended strongly on reference quality. ColorChecker chart correction is widely used in photography and printing, yet covering each UAV view is impractical in field missions. These limitations highlighted the need for a real-time, mobile, and scalable color standardization method for agricultural remote sensing.

A study (DOI: 10.1016/j.plaphe.2025.100101) published in Plant Phenomics on 5 September 2025 by Haiyan Cen’s team, Zhejiang University, demonstrates a reliable dual-UAV color correction method that significantly enhances the accuracy and consistency of field-scale RGB imagery, enabling more precise crop phenotyping and agricultural decision-making.

A evaluation was performed to verify the performance of the CoF-CC color correction method, beginning with tests across six different camera models in which images containing both the ColorChecker and rice fields were captured and corrected using a color correction matrix. Results showed that the method successfully reduced brightness and color discrepancies among original images, lowering the ΔE values of ColorChecker patches from 5.8–18.0 to 3.4–5.0, reflecting a 66.1% improvement in color accuracy. Color distributions plotted in LAB 3D space revealed tighter clusters after correction, and the intracluster distance decreased from 13.2 to 3.9, indicating a 70.2% enhancement in color consistency. Further accuracy assessment using large-scale field images confirmed these outcomes, with ΔE values across variable image sets dropping from 8.0–25.9 to 2.3–8.2, representing a 73.6% increase in accuracy. When color-cast images were corrected, artificial distortions were reduced to an average ΔE of 7.1. Comparisons with ground-truth measurements at 30 sampling points showed mean ΔE reduced from 18.2 to 5.0—a 72.7% improvement. The corrected images also enabled clearer visualization of ripening differences. To evaluate segmentation effectiveness, ground-truth leaf colors were mapped onto both original and corrected images. Original segmentation poorly matched actual leaf shapes, but corrected images aligned well with manual labeling, increasing overlap from 15.1% to 64.3%, demonstrating significantly improved target identification. Finally, the corrected orthomosaic allowed extraction of canopy color values for each plot, effectively differentiating breeding materials. While original image colors showed weak correlation with rice maturity (R² = 0.28), CoF-CC–derived colors achieved a strong linear relationship (R² = 0.67), confirming the method's value for phenotyping and maturity prediction.

Accurate field-scale color measurement plays a vital role in agricultural decision-making, supporting genotype evaluation in breeding nurseries, crop stress and nutrient assessment, harvest timing estimation, digital phenotyping, and large-scale monitoring for precision agriculture. By tightly leveraging the relationship between canopy color, chlorophyll content, and maturity, the CoF-CC pipeline ensures reliable extraction of color-based signals that are often masked by illumination variation, marking an important step toward standardized RGB datasets, improved data sharing across experiments, and scalable high-throughput phenotyping and automation in modern agriculture.

###

References

DOI

10.1016/j.plaphe.2025.100101

Original Source URl

https://doi.org/10.1016/j.plaphe.2025.100101

Funding information

This work was funded by the International S&T Cooperation Program of China (2024YFE0115000), the National Key R & D Program of China (2021YFD2000104), the National Natural Science Foundation of China (32371985), and the Fundamental Research Funds for Central Universities (226-2022-00217).

About Plant Phenomics

Plant Phenomics is dedicated to publishing novel research that will advance all aspects of plant phenotyping from the cell to the plant population levels using innovative combinations of sensor systems and data analytics. Plant Phenomics aims also to connect phenomics to other science domains, such as genomics, genetics, physiology, molecular biology, bioinformatics, statistics, mathematics, and computer sciences. Plant Phenomics should thus contribute to advance plant sciences and agriculture/forestry/horticulture by addressing key scientific challenges in the area of plant phenomics.

---

Journal

Plant Phenomics

DOI

10.1016/j.plaphe.2025.100101 

Method of Research

Experimental study

Subject of Research

Not applicable

Article Title

Precise Image Color Correction Based on Dual Unmanned Aerial Vehicle Cooperative Flight

Deep-learning model predicts how fruit flies form, cell by cell

The approach could apply to more complex tissues and organs, helping researchers to identify early signs of disease.

Massachusetts Institute of Technology

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

During early development, tissues and organs begin to bloom through the shifting, splitting, and growing of many thousands of cells. 

A team of MIT engineers has now developed a way to predict, minute by minute, how individual cells will fold, divide, and rearrange during a fruit fly’s earliest stage of growth. The new method may one day be applied to predict the development of more complex tissues, organs, and organisms. It could also help scientists identify cell patterns that correspond to early-onset diseases, such as asthma and cancer. 

In a study appearing in the journal Nature Methods, the team presents a new deep-learning model that learns, then predicts, how certain geometric properties of individual cells will change as a fruit fly develops. The model records and tracks properties such as a cell’s position, and whether it is touching a neighboring cell at a given moment. 

The team applied the model to videos of developing fruit fly embryos, each of which starts as a cluster of about 5,000 cells. They found the model could predict, with 90 percent accuracy, how each of the 5,000 cells would fold, shift, and rearrange, minute by minute, during the first hour of development, as the embryo morphs from a smooth, uniform shape into more defined structures and features. 

“This very initial phase is known as gastrulation, which takes place over roughly one hour, when individual cells are rearranging on a time scale of minutes,” says study author Ming Guo, associate professor of mechanical engineering at MIT. “By accurately modeling this early period, we can start to uncover how local cell interactions give rise to global tissues and organisms.” 

The researchers hope to apply the model to predict the cell-by-cell development in other species, such zebrafish and mice. Then, they can begin to identify patterns that are common across species. The team also envisions that the method could be used to discern early patterns of disease, such as in asthma. Lung tissue in people with asthma looks markedly different from healthy lung tissue. How asthma-prone tissue initially develops is an unknown process that the team’s new method could potentially reveal. 

“Asthmatic tissues show different cell dynamics when imaged live,” says co-author and MIT graduate student Haiqian Yang. “We envision that our model could capture these subtle dynamical differences and provide a more comprehensive representation of tissue behavior, potentially improving diagnostics or drug-screening assays.”

The study’s co-authors are Markus Buehler, the McAfee Professor of Engineering in MIT’s Department of Civil and Environmental Engineering; George Roy and Tomer Stern of the University of Michigan; and Anh Nguyen and Dapeng Bi of Northeastern University.

Points and foams

Scientists typically model how an embryo develops in one of two ways: as a point cloud, where each point represents an individual cell as point that moves over time; or as a “foam,” which represents individual cells as bubbles that shift and slide against each other, similar to the bubbles in shaving foam. 

Rather than choose between the two approaches, Guo and Yang embraced both. 

“There’s a debate about whether to model as a point cloud or a foam,” Yang says. “But both of them are essentially different ways of modeling the same underlying graph, which is an elegant way to represent living tissues. By combining these as one graph, we can highlight more structural information, like how cells are connected to each other as they rearrange over time.”

At the heart of the new model is a “dual-graph” structure that represents a developing embryo as both moving points and bubbles. Through this dual representation, the researchers hoped to capture more detailed geometric properties of individual cells, such as the location of a cell’s nucleus, whether a cell is touching a neighboring cell, and whether it is folding or dividing at a given moment in time. 

As a proof of principle, the team trained the new model to “learn” how individual cells change over time during fruit fly gastrulation. 

“The overall shape of the fruit fly at this stage is roughly an ellipsoid, but there are gigantic dynamics going on at the surface during gastrulation,” Guo says. “It goes from entirely smooth to forming a number of folds at different angles. And we want to predict all of those dynamics, moment to moment, and cell by cell.” 

Where and when

For their new study, the researchers applied the new model to high-quality videos of fruit fly gastrulation taken by their collaborators at the University of Michigan. The videos are one-hour recordings of developing fruit flies, taken at single-cell resolution. What’s more, the videos contain labels of individual cells’ edges and nuclei — data that are incredibly detailed and difficult to come by. 

“These videos are of extremely high quality,” Yang says. “This data is very rare, where you get submicron resolution of the whole 3D volume at a pretty fast frame rate.” 

The team trained the new model with data from three of four fruit fly embryo videos, such that the model might “learn” how individual cells interact and change as an embryo develops. They then tested the model on an entirely new fruit fly video, and found that it was able to predict with high accuracy how most of the embryo’s 5,000 cells changed from minute to minute. 

Specifically, the model could predict properties of individual cells, such as whether they will fold, divide, or continue sharing an edge with a neighboring cell, with about 90 percent accuracy. 

“We end up predicting not only whether these things will happen, but also when,” Guo says. “For instance, will this cell detach from this cell seven minutes from now, or eight? We can tell when that will happen.”

The team believes that, in principle, the new model, and the dual-graph approach, should be able to predict the cell-by-cell development of other multiceullar systems, such as more complex species, and even some human tissues and organs. The limiting factor is the availability of high-quality video data. 

“From the model perspective, I think it’s ready,” Guo says. “The real bottleneck is the data. If we have good quality data of specific tissues, the model could be directly applied to predict the development of many more structures.”

This work is supported, in part, by the U.S. National Institutes of Health.

###

Written by Jennifer Chu, MIT News

---

Journal

Nature Methods

Article Title

“MultiCell: geometric learning in multicellular development”

 

 

How 3D printing creates stronger vehicle parts by solving aluminum’s high-temperature weakness 

Nagoya University researchers break conventional rules to develop heat-resistant, recyclable metal alloys for automotive and aerospace use

Peer-Reviewed Publication

Nagoya University

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Microscope image showing the layered structure of a new 3D-printed aluminum alloy. The wave-like patterns are “melt pools,” traces left by the laser as it melted metal powder layer by layer. The small dark dots are nanoscale particles that give the alloy its exceptional strength and heat resistance. 

view more 

Credit: Takata et al., 2025

Aluminum is prized for being lightweight and strong, but at high temperatures it loses strength. This has limited its use in engines, turbines, and other applications where parts must stay strong under high temperature conditions. Researchers at Nagoya University have developed a method that uses metal 3D printing to create a new aluminum alloy series optimized for high strength and heat resistance. All new alloys use low-cost, abundant elements, and are recycling-friendly, with one variant staying both strong and flexible at 300°C. The study was published in Nature Communications. 
 
Breaking with tradition to create the perfect aluminum alloy 


“The design centers on iron, which metallurgists usually don’t add to aluminum because it makes the metal brittle and vulnerable to corrosion,” Naoki Takata, lead author and professor at Nagoya University Graduate School of Engineering, explained. 

“The extreme cooling rates in laser powder bed fusion, which is a representative process of metal 3D printing technologies, cause molten metal to solidify in seconds. This changes fundamental rules—the rapid cooling traps iron and other elements in arrangements (formation of metastable phases) that can’t form under normal manufacturing conditions. By carefully selecting which elements to add, we created new alloys that are both heat-resistant and strong.” 

The researchers developed a systematic method to predict which elements will strengthen the aluminum matrix and which will form protective micro or nano structures. They tested these predictions by creating new alloys with copper, manganese, and titanium, and then confirmed the results through electron microscopy. 

The best performing alloy contains aluminum, iron, manganese, and titanium (Al-Fe-Mn-Ti), and outperforms all other 3D-printed aluminum materials by combining strength at high temperatures with flexibility at room temperature.

“Our method relies on established scientific principles about how elements behave during rapid solidification in 3D printing and is applicable to other metals. The alloys also proved easier to 3D print than conventional high-strength aluminum, which frequently cracks or warps during fabrication,” Professor Takata noted. 
 
Lighter vehicles, fewer emissions

The new materials could enable lightweight aluminum components in parts that operate at elevated temperatures, such as compressor rotors and turbine components. Lighter vehicles consume less fuel and produce fewer emissions. 

The aerospace industry may also benefit, as aircraft engines require materials that combine light weight with heat resistance. Beyond these applications, the research provides a framework for designing new classes of metals specifically for 3D printing, with potential to accelerate development across multiple industries.

Microscopic views of aluminum alloys after 3D printing. Row 1: How the metal melts and solidifies in layers. Row 2: The internal grain structure that affects strength. Row 3: Tiny particles inside the metal that help make it stronger. Row 4: Similar particles at the edges that influence how the material behaves under stress.

Credit

Takata et al., 2025

Fine metal powder used to 3D print the new aluminum alloys. Each particle is less than 20 micrometers in diameter. A laser melts these particles layer by layer to build the final metal part.  

Credit

Merle Naidoo

Naoki Takata of Nagoya University, lead researcher on the project (left), and Masaki Kato, senior author and division head of Aichi Center for Industry and Science Technology (right), with the center's laser 3D printer that creates stronger, heat-resistant aluminum alloys layer by layer.

Credit

Merle Naidoo, Nagoya University

Journal

Nature Communications

DOI

10.1038/s41467-025-67281-8 

Method of Research

Experimental study

Subject of Research

Not applicable

Article Title

Design of high-performance sustainable aluminum alloy series for laser additive manufacturing

Article Publication Date

15-Dec-2025

Saving lives, not raising birthrates, is Eastern Europe’s best hope against population decline

International Institute for Applied Systems Analysis

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

European governments worried about population decline often focus on policies to encourage people to have more children. However, a new study reveals that this popular strategy is often less effective and more ethically problematic than a simpler, immediate alternative: large-scale investment in public health to reduce preventable deaths.

The research, conducted by an international team of demographers including IIASA Distinguished Emeritus Research Scholar Sergei Scherbov, analyzed population trends across 80 low-fertility countries. Among them, the researchers identified 28 countries – mostly in Eastern and South-Eastern Europe – where dramatically reducing mortality, especially premature mortality, would slow population decline more effectively than raising birth rates.

The top 10 countries projected to see the greatest relative population decline by 2050 are all in Europe, with nations like Bulgaria, Ukraine, Latvia, and Russia showing the highest potential for impact.

For the first time, researchers compared two ambitious population strategies:

• Instant replacement fertility: assuming a country’s birth rate immediately jumps to 2.1 children per woman (the “replacement” level), the goal of many pronatalist policies.
• Japanese mortality levels: assuming a country’s health systems improve instantly to match Japan’s world-leading low mortality rates.

The results show a stark difference. For the 13 European countries facing a projected population decline of 5% or more by 2050, the findings are clear:

• The total population of these countries is currently projected to fall by 33.8 million people by 2050 without intervention.
• If they achieved the (highly unlikely) jump to replacement fertility, the population loss would slow down, reducing the total decline to 14.1 million.
• Crucially, if they reduced their mortality rates to match Japan’s, the total population decline would shrink to only 1.7 million.

“In the countries most affected by population decline, which are predominantly in Eastern and South-Eastern Europe, achieving Japanese mortality levels would reduce the predicted population loss from 33.8 million to just 1.7 million people,” says Stuart Gietel-Basten, study coauthor from The Hong Kong University of Science and Technology. “This far outperforms the benefits expected from pushing for more births. It’s an empirical demonstration that saving the lives of people already here is the most powerful demographic tool available.”

The authors argue that focusing on lowering mortality offers multiple advantages over pronatalist policies, which often fail to achieve long-term fertility increases and can sometimes infringe on reproductive rights by limiting access to sexual and reproductive health services.

The researchers recommend that policymakers shift their focus to strengthening health systems, improving disease prevention, and implementing public health interventions – especially those targeting high male mortality from issues like alcohol abuse and poor diet in Eastern Europe.

The analysis concludes that reducing preventable and treatable mortality should be the central pillar of any demographic strategy, offering a more effective, immediate, and human-rights-aligned response to concerns over population decline.

“Governments have already made massive investments in citizens’ education and health,” says Scherbov. “When people die prematurely from preventable diseases, that societal investment is lost. Saving those lives means maximizing the return on investment in our existing population, allowing them to continue contributing to the economy and society for longer.”

“While our study focused specifically on Europe, the imperative to invest in human life and health is a universal lesson for all nations facing a future of demographic change,” concludes coauthor, Wiraporn Pothisiri, from the College of Population Studies, Chulalongkorn University, Bangkok, Thailand.

Reference
Gietel-Basten, S., Pothisiri, W., & Scherbov, S. (2025). Investments in health and mortality reduction to address population decline. Bulletin of the World Health Organization; Type: Policy & practice. Article ID: BLT.25.293627

 

About IIASA:
The International Institute for Applied Systems Analysis (IIASA) is an international scientific institute that conducts research into the critical issues of global environmental, economic, technological, and social change that we face in the twenty-first century. Our findings provide valuable options to policymakers to shape the future of our changing world. IIASA is independent and funded by prestigious research funding agencies in Africa, the Americas, Asia, and Europe. www.iiasa.ac.at

---

Journal

Bulletin of the World Health Organization

Article Title

Investments in health and mortality reduction to address population decline

Article Publication Date

2-Dec-2025