There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Three parallel algorithms for classical molecular dynamics are presented. The first assigns each processor a fixed subset of atoms; the second assigns each a fixed subset of inter-atomic forces to compute; the third assigns each a fixed spatial region. The algorithms are suitable for molecular dynamics models which can be difficult to parallelize efficiently—those with short-range forces where the neighbors of each atom change rapidly. They can be implemented on any distributed-memory parallel machine which allows for message-passing of data between independently executing processors. The algorithms are tested on a standard Lennard-Jones benchmark problem for system sizes ranging from 500 to 100,000,000 atoms on several parallel supercomputers--the nCUBE 2, Intel iPSC/860 and Paragon, and Cray T3D. Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems. For large problems, the spatial algorithm achieves parallel efficiencies of 90% and a 1840-node Intel Paragon performs up to 165 faster than a single Cray C9O processor. Trade-offs between the three algorithms and guidelines for adapting them to more complex molecular dynamics simulations are also discussed.

Fast parallel algorithms for short-range molecular dynamics

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Crop diseases are a major threat to food security, but their rapid identification remains difficult in many parts of the world due to the lack of the necessary infrastructure. The combination of increasing global smartphone penetration and recent advances in computer vision made possible by deep learning has paved the way for smartphone-assisted disease diagnosis. Using a public dataset of 54,306 images of diseased and healthy plant leaves collected under controlled conditions, we train a deep convolutional neural network to identify 14 crop species and 26 diseases (or absence thereof). The trained model achieves an accuracy of 99.35% on a held-out test set, demonstrating the feasibility of this approach. Overall, the approach of training deep learning models on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a massive global scale.

/pdf/using-deep-learning-for-image-based-plant-disease-detection-3ep7b222h5.pdf

Using Deep Learning for Image-Based Plant Disease Detection

Deep learning in agriculture: A survey

Insect-pests significantly impact global agricultural productivity and quality. Effective management involves identifying the full insect community, including beneficial insects and harmful pests, to develop and implement integrated pest management strategies. Automated identification of insects under real-world conditions presents several challenges, including differentiating similar-looking species, intra-species dissimilarity and inter-species similarity, several life cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. A deep-learning model, InsectNet, is proposed to address these challenges. InsectNet is endowed with five key features: (a) utilization of a large dataset of insect images collected through citizen science; (b) label-free self-supervised learning for large models; (c) improving prediction accuracy for species with a small sample size; (d) enhancing model trustworthiness; and (e) democratizing access through streamlined MLOps. This approach allows accurate identification (>96% accuracy) of over 2500 insect species, including pollinator (e.g., butterflies, bees), parasitoid (e.g., some wasps and flies), predator species (e.g., lady beetles, mantises, dragonflies) and harmful pest species (e.g., armyworms, cutworms, grasshoppers, stink bugs). InsectNet can identify invasive species, provide fine-grained insect species identification, and work effectively in challenging backgrounds. It also can abstain from making predictions when uncertain, facilitating seamless human intervention and making it a practical and trustworthy tool. InsectNet can guide citizen science data collection, especially for invasive species where early detection is crucial. Similar approaches may transform other agricultural challenges like disease detection and underscore the importance of data collection, particularly through citizen science efforts..

Deep learning powered real-time identification of insects using citizen science data

Sensors in the built environment ensure safety and comfort by tracking contaminants in the occupied space. In the event of contaminant release, it is important to use the limited sensor data to rapidly and accurately identify the release location of the contaminant. Identification of the release location will enable subsequent remediation as well as evacuation decision-making. In previous work, we used an operator theoretic approach—based on the Perron–Frobenius (PF) operator—to estimate the contaminant concentration distribution in the domain given a finite amount of streaming sensor data. In the current work, the approach is extended to identify the most probable contaminant release location. The release location identification is framed as a Bayesian inference problem. The Bayesian inference approach requires considering multiple release location scenarios, which is done efficiently using the discrete PF operator. The discrete PF operator provides a fast, effective and accurate model for contaminant transport modeling. The utility of our PF-based Bayesian inference methodology is illustrated using single-point release scenarios in both two and three-dimensional cases. The method provides a fast, accurate, and efficient framework for real-time identification of contaminant source location.

Contaminant Source Identification from Finite Sensor Data: Perron–Frobenius Operator and Bayesian Inference


 The ongoing COVID-19 pandemic has rendered confined spaces as high-risk areas. There is an increasing push to resume in-person activities, for instance, teaching in K-12 and university settings. It becomes important to evaluate the risk of airborne disease transmission while accounting for the physical presence of humans, furniture, and electronic equipment, as well as ventilation. Here, we present a computational framework based on detailed flow physics simulations that allows straightforward evaluation of various seating and operating scenarios to identify risk factors and assess the effectiveness of various mitigation strategies. These scenarios include seating arrangement changes, presence/absence of computer screens, ventilation rate changes, and presence/absence of mask-wearing. This approach democratizes risk assessment by automating a key bottleneck in simulation-based analysis--creating an adequately refined mesh around multiple complex geometries. Not surprisingly, we find that wearing masks (with at least 74% inward protection efficiency) significantly reduced transmission risk against unmasked and infected individuals. The availability of such an analysis approach will allow education administrators, government officials (courthouses, police stations), and hospital administrators to make informed decisions on seating arrangements and operating procedures.

/pdf/a-computational-framework-for-transmission-risk-assessment-3hyks5n3wb.pdf

A Computational Framework for Transmission Risk Assessment of Aerosolized Particles in Classrooms

Soybean yield prediction is a challenging problem in plant breeding that is often affected by many different factors simultaneously. Hyperspectral reflectance data from plants provide breeders with useful data about the health of soybean plants and using this data for yield prediction is an active area of research. Often breeding programs suffer from issues such as data imbalance and several external factors such as genotype variablility in different environments which can pose a serious challenge for developing yield prediction models for large scale breeding programs. In this work we demonstrate a cluster based ensemble approach for yield prediction that can perform well for large scale breeding programs by efficiently harnessing useful information from data through an unsupervised approach.

Data driven ensemble learning for soybean yield prediction

Score-based methods, particularly denoising diffusion probabilistic models (DDPMs), have demonstrated impressive improvements to state-of-the-art generative modeling. Due to their impressive ability to sample from complex distributions, DDPM models and related variants, all broadly categorized under diffusion models, apply to various applications. In this work, we compare the performance of a diffusion model with a Wasserstein Generative Adversarial Network in generating two-phase microstructures of photovoltaic cells. We demonstrate the diffusion model’s performance improvements in generating realistic-looking microstructures and its ability to cover several modes of the target distribution.

Baskar Ganapathysubramanian

Papers

Deep learning powered real-time identification of insects using citizen science data

Contaminant Source Identification from Finite Sensor Data: Perron–Frobenius Operator and Bayesian Inference

A Computational Framework for Transmission Risk Assessment of Aerosolized Particles in Classrooms

Data driven ensemble learning for soybean yield prediction

Generative Design of Material Microstructures for Organic Solar Cells using Diffusion Models