The study, published in the journal Smart Agricultural Technology, was conducted by Jobin Francis, Ali Al Masri, Maximilian Pircher, and Philipp Wree, who set out to solve a problem that has long limited plant disease detection research: most hyperspectral imaging studies are performed in laboratories, where lighting, sample orientation, and ambient conditions can be carefully controlled. Real fields are far messier. Fluctuating illumination, wind, temperature shifts, and inconsistent leaf positioning can all degrade spectral data and undermine model performance. Because diseases like powdery mildew actually occur in open-field settings, the team deliberately chose to acquire data from strawberry plants growing under a semi-controlled polytunnel, a step closer to the conditions a working farm would face.

The experimental setup was elegantly practical. A Cubert X20 hyperspectral video camera, covering wavelengths from 350 to 1000 nanometers across 164 spectral bands, was mounted on a mechanized trolley that traveled along overhead rails above the strawberry canopy. The camera captured images at regular intervals with centimeter-precise localization, sweeping over the plants much as a robotic scouting platform might in a commercial operation. Crucially, no artificial inoculation was performed; powdery mildew occurred naturally on the leaves and progressed in severity over several weeks, meaning the study captured the disease exactly as it presents in the real world.

Calibration was treated as a make-or-break step. Before each acquisition session, the researchers performed dark calibration by covering the lens with an opaque cap, white calibration using a Spectralon tile with 99.9 percent reflectance, and distance calibration to fix the camera-to-object spacing. Raw images were then converted to calibrated reflectance values by subtracting the dark reference and normalizing against the white reference. But the team went further: as the camera moved along the rail, subtle drifts crept in from changing ambient light, shifting leaf orientation, and mechanical vibration. They therefore continuously compared each new frame’s spectral signatures against a reference spectrum from healthy leaves, and once deviations exceeded an acceptable threshold, all subsequent data were discarded. Only spectrally consistent, well-calibrated frames made it into the modeling pipeline, a discipline the authors credit for the robustness of their results.

The underlying physics of the detection method is what makes hyperspectral imaging so powerful. Healthy strawberry leaves show low reflectance across the visible range of 400 to 700 nanometers, with a characteristic green peak between 500 and 570 nanometers, a nitrogen absorption band near 550 nanometers, and a deep reflectance valley around 670 nanometers caused by strong chlorophyll absorption. Beyond that lies the sharp rise at the red edge and high reflectance in the near-infrared, where healthy leaf structure scatters light efficiently. Infected leaves tell a different story. Powdery mildew alters photochemical activity and pigment content, and these biochemical shifts show up as measurable deviations in the spectral fingerprint long before any human eye could see a lesion. Because molecular absorption depends on cellular composition, the disease essentially rewrites the leaf’s chemical signature in ways the camera can read.

Turning those raw spectra into a reliable classifier required careful preprocessing. The team first applied an Isolation Forest algorithm, an unsupervised outlier detection method that removes anomalous spectra caused by noisy measurements or inconsistent illumination. Next came Savitzky-Golay smoothing, which suppresses high-frequency noise while preserving the shape of the spectral curves. Two scatter-correction strategies were then evaluated: Standard Normal Variate and Multiplicative Scatter Correction, both designed to normalize each spectrum relative to the dataset mean and correct for scattering effects. The cleaned spectral data were extracted from regions of interest identified on RGB-equivalent composite images, yielding a balanced dataset of 1,940 spectra, evenly split between healthy and mildew-affected leaves.

For classification, the researchers built a one-dimensional convolutional neural network tailored to spectral data. Each spectrum was treated as a one-dimensional signal of 145 bands, fed into a compact architecture of four convolutional layers with 32, 64, and 128 filters, each using kernel size 3 and ReLU activation. Batch normalization stabilized training after every convolutional layer, while max-pooling layers reduced feature dimensions. The flattened features passed through a dense layer of 64 neurons, a dropout layer with a rate of 0.3 to prevent overfitting, and finally a sigmoid output neuron for the binary healthy-versus-mildew decision. Training used the Adam optimizer with binary cross-entropy loss, a learning rate of 0.0001, and 100 epochs on a stratified 70:15:15 split of the data.

The results were striking. Training accuracy climbed rapidly in the first 10 to 15 epochs and settled at 0.84, while validation accuracy stabilized between 0.83 and 0.86. On the independent test set, the network correctly identified 137 of 145 mildew samples, missing only 8 infections, while 108 of 146 healthy samples were correctly classified. The model achieved an area under the ROC curve of 0.933, indicating strong separability across all decision thresholds. Notably, the operating point favored sensitivity to disease: mildew recall reached 0.94, and most errors were false alarms on healthy leaves rather than missed infections, a favorable trade-off for screening scenarios where a missed case is far costlier than an unnecessary inspection. Because the ROC profile is strong, growers could recalibrate the decision threshold to suit their needs without retraining the model.

The deep learning approach also outperformed classical machine learning baselines trained on the same data. Random Forest led the traditional methods with an accuracy of 0.81 and an F1-score of 0.82, benefiting from its ability to capture non-linear spectral relationships. Decision Tree and Partial Least Squares Discriminant Analysis achieved moderate accuracies of 0.77 and 0.79 respectively, while a support vector machine with an RBF kernel struggled, showing a pronounced bias toward the healthy class and an accuracy of just 0.68. The comparison underscores a key advantage of the convolutional network: it learns discriminative features automatically from raw spectra rather than depending on manual feature engineering, and it offers more tunable operating characteristics for real-world deployment.

Perhaps the most commercially significant finding came from the wavelength selection pipeline. Because hyperspectral cubes contain hundreds of highly correlated bands, many of which carry noise or redundancy, the team developed a two-stage filter: first pruning wavelengths with variance below 0.001, then ranking the survivors by mutual information with the disease labels and keeping the most informative bands, expanded by their two nearest spectral neighbors to preserve local context. This compact band set concentrated on pigment- and structure-sensitive regions of the spectrum, and when fed into the network it improved test accuracy to 0.894 and pushed the AUC to 0.968, all while dramatically reducing input dimensionality. The authors point out that such a band set could directly inform the design of lightweight multispectral sensors with filters near the red edge and near-infrared clusters, paving the way for affordable, field-ready disease scouting systems. Future work, they note, should expand the dataset across cultivars, growth stages, and seasons, integrate spatial-spectral context through patch-based architectures, and calibrate decision thresholds to the specific costs of missed disease versus false alarms. If those steps succeed, the combination of hyperspectral sensing and deep learning could move from the research polytunnel to the commercial greenhouse, giving strawberry growers a real-time shield against one of their costliest foes.

Subject of Research: Hyperspectral imaging and deep learning detection of powdery mildew in strawberry leaves under polytunnel conditions

Article Title: Hyperspectral imaging and one–dimensional convolutional neural network (1D-CNN) based detection of strawberry powdery mildew under polytunnel conditions

Article References: Francis, J., Al Masri, A., Pircher, M., & Wree, P. (2026). Hyperspectral imaging and one–dimensional convolutional neural network (1D-CNN) based detection of strawberry powdery mildew under polytunnel conditions. Smart Agricultural Technology, 15, Article 102603. https://doi.org/10.1016/j.atech.2026.102603

Image Credits: AI Generated

DOI: 10.1016/j.atech.2026.102603

Keywords: hyperspectral imaging, powdery mildew, strawberry, 1D-CNN, deep learning, precision agriculture, plant disease detection, polytunnel, wavelength selection, machine learning, early disease diagnosis, smart farming

The innovative work builds upon the understanding of RNA, a type of nucleic acid that governs various cellular activities. The implications of this research could revolutionize medical diagnostics. Imagine a future where individuals visit healthcare facilities and provide samples of their own cells during routine check-ups. Researchers envision a scenario where the technology could convert these ordinary cells into sophisticated sensor cells, thereby retaining their natural characteristics and biological integrity. Such a system would potentially eliminate the body’s immune response, as the reintroduced cells are derived from the individual’s own body. This methodology could offer a more personalized approach to health monitoring by enabling these sensor cells to relay vital information regarding the presence of harmful chemicals or incipient health issues.

Published in the prestigious journal Angewandte Chemie International Edition, this research led by Assistant Professor Enver Cagri Izgu and his team demonstrates the effective integration of RNA in bacterial cells, allowing these cells and their progeny to detect specific chemicals with remarkable precision. Traditionally, RNA has been limited in its interaction with certain inorganic substances, making it challenging to develop effective genetic circuits for chemical sensing. However, this new approach overcomes these hurdles and innovatively utilizes RNA to interact with short-lived inorganic chemicals integral to various physiological functions, both in healthy individuals and those afflicted by illness.

The ingenious technique described in their study involves a unique receptor molecule that undergoes a chemical reaction with the target inorganic chemical. This interaction then allows the receptor to bind with a specially engineered RNA sequence, culminating in a binding event that results in light emission at a defined wavelength. The researchers successfully executed this chemical sensing mechanism within living Escherichia coli, which serves as an ideal model organism for such experiments. The ability to generate light as a response to chemical interactions not only provides a novel detection method but also adds an exciting visual dimension to the sensing process.

What is particularly striking about this research is its novelty. While there has been progress in producing custom-designed RNA within cells, no prior methods successfully employed RNA to actively detect small inorganic chemicals like hydrogen sulfide and hydrogen peroxide. The ability to achieve this in live bacterial systems opens new avenues for biosensing applications since changes in hydrogen sulfide and hydrogen peroxide levels have been tightly linked to the pathology of numerous conditions, including cancer and cardiovascular and neurological diseases.

Izgu emphasized the broader goal of this research: to harness the same techniques applied to bacteria and translate them into human cells. The vision is to modify human cells into sensor cells that could continuously monitor for critical biochemical changes. By replicating their success in E. coli, researchers hope to pave the way for innovative diagnostic technologies that could eventually lead to breakthroughs in personalized medicine, enhancing our capability to detect diseases earlier and with more accuracy.

Co-author Tushar Aggarwal, who is noted in the research as a former doctoral student in the Department of Chemistry and Chemical Biology, further contributes to the project’s impending commercial viability. Together with Izgu, he is a co-inventor on a patent application submitted on this pioneering work, which signifies the importance of their findings not only in academic circles but also in the potential marketplace for health technologies.

The research team also profiled other contributors who played vital roles in advancing the study. Liming Wang and Sarah Cho, both current doctoral students, along with former student Bryan Gutierrez, have been instrumental in pushing the boundaries of research in this area. Further contributions came from Huseyin Erguven, a previous postdoctoral associate, and Hakan Guven, a current student at Robert Wood Johnson Medical School, thus demonstrating a rich collaboration that spans multiple academic levels and expertise.

As the scientific community continues to explore and unravel the multifaceted functions of RNA, this research underscores the remarkable potential of RNA-based technologies. The findings not only expand our comprehension of the biochemical roles of RNA but also inspire future research endeavors aimed at enhancing human health through innovative biosensing methods.

With ongoing studies into RNA’s capabilities, further breakthroughs are anticipated, potentially leading to additional discoveries that may redefine how we approach disease prevention and surveillance. The unwavering commitment of researchers at Rutgers University signals an exciting shift toward a future where innovative biosensors could become commonplace in medical diagnostics, increasing the efficacy of early disease detection and environmental monitoring.

Ultimately, this research is a crucial step forward in the integration of computer-like sensing capabilities within biological systems, marrying the worlds of technology and biology into a cohesive unit that promotes health and wellness in unprecedented ways. As we look ahead to what these advances could mean for healthcare, it is clear that the fusion of RNA research with cutting-edge biosensing technology may fundamentally change our approach to human health and disease management.

As such, the promise of this groundbreaking research extends beyond the laboratory and invites us to envision a future where our biological systems actively work to safeguard our health by monitoring the very markers of disease from within.

Subject of Research: Cells
Article Title: A Small-Molecule Approach Enables RNA Aptamers to Function as Sensors for Reactive Inorganic Targets
News Publication Date: 17-Mar-2025
Web References: DOI 10.1002/anie.202421936
References: None
Image Credits: Enver Izgu/Rutgers University

Keywords: RNA, biosensor, human health, disease detection, environmental monitoring, Escherichia coli, cancer, cardiovascular, neurological diseases, personalized medicine.