We describe ChemBO, a Bayesian Optimization framework for generating and optimizing organic molecules for desired molecular properties. This framework is useful in applications such as drug discovery, where an algorithm recommends new candidate molecules; these molecules first need to be synthesized and then tested for drug-like properties. The algorithm uses the results of past tests to recommend new ones so as to find good molecules efficiently. Most existing data-driven methods for this problem do not account for sample efficiency and/or fail to enforce realistic constraints on synthesizability. In this work, we explore existing kernels for molecules in the literature as well as propose a novel kernel which views a molecule as a graph. In ChemBO, we implement these kernels in a Gaussian process model. Then we explore the chemical space by traversing possible paths of molecular synthesis. Consequently, our approach provides a proposal synthesis path every time it recommends a new molecule to test, a crucial advantage when compared to existing methods. In our experiments, we demonstrate the efficacy of the proposed approach on several molecular optimization problems.

In recent years, machine learning has been proving a valuable tool for identifying new materials with properties optimized for specific applications. Working with large, well-defined data sets, computers learn to perform an analytical task to generate a correct answer and then use the same technique on an unknown data set. While that approach has guided the development of valuable new materials, they've primarily been organic compounds, notes Heather Kulik Ph.D. '09, an assistant professor of chemical engineering. Kulik focuses instead on inorganic compounds--in particular, those based on transition metals, a family of elements (including iron and copper) that have unique and useful properties. In those compounds--known as transition metal complexes--the metal atom occurs at the center with chemically bound arms, or ligands, made of carbon, hydrogen, nitrogen, or oxygen atoms radiating outward. Transition metal complexes already play important roles in areas ranging from energy storage to catalysis for manufacturing fine chemicals--for example, for pharmaceuticals.

LONDON - In decades to come, African farmers may pool their money to buy small robot vehicles to weed their fields or drones that can hover to squirt a few drops of pesticide only where needed. Smartphones already allow farmers in remote areas to snap photos of sick plants, upload them and get a quick diagnosis, plus advice on treatment. Researchers also are trying to train crops like maize and wheat to produce their own nitrogen fertilizer from the air -- a trick soybeans and other legumes use -- and exploring how to make wheat and rice better at photosynthesis in very hot conditions. As warmer, wilder weather linked to climate change brings growing challenges for farmers across the globe -- and as they try to curb their own heat-trapping emissions -- a rush of innovation aimed at helping both rich and poor farmers is now converging in ways that could benefit them all, scientists say. In a hotter world, farmers share "the same problems, the same issues," said Svend Christensen, head of plant and environmental sciences at the University of Copenhagen.

This article was written by Kate Crawford & Vladan Joler. Below is an extract, featuring the first three sections of this long article (21 sections total.) Link to the full article is provided at the bottom. A cylinder sits in a room. It is impassive, smooth, simple and small.

In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven health monitoring systems is gaining in popularity due to the large availability of data from low-cost sensors with internetworking capabilities. In particular, deep learning provides the tools for processing and analyzing this unprecedented amount of data efficiently. The main purpose of this paper is to combine the recent advances of Deep Learning (DL) and statistical analysis on structural health monitoring (SHM) to develop an accurate classification tool able to discriminate among different acoustic emission events (cracks) by means of the identification of tensile, shear and mixed modes. The applications of DL in SHM systems is described by using the concept of Bidirectional Long Short Term Memory. We investigated on effective event descriptors to capture the unique characteristics from the different types of modes. Among them, Spectral Kurtosis and Spectral L2/L1 Norm exhibit distinctive behavior and effectively contributed to the learning process. This classification will contribute to unambiguously detect incipient damages, which is advantageous to realize predictive maintenance. Tests on experimental results confirm that this method achieves accurate classification (92%) capabilities of crack events and can impact on the design of future SHM technologies.

It's rare to see tech headlines about agriculture, but the field (pardon the pun) is often at the forefront of implementing new technology Perhaps no recent tech development has had a greater impact on the industry than smart technology, and this IoT data is being used to improve operations across nearly all modern farming operations around the globe. Here are a few examples. Farmers were among the first to adopt GPS technology; John Deere was the first tractor manufacturer to implement GPS technologies in the early 1990s, and farmers quickly began using GPS assistance and even automated steering to reduce user errors. GPS technology can be combined with sensor data to create ultra-precise maps of varying factors. Knowing how soil quality varies across large plots of land, for example, can help farmers know which areas need which type of fertilizers.

Machine learning recently has been used to identify the governing equations for dynamics in physical systems. The promising results from applications on systems such as fluid dynamics and chemical kinetics inspire further investigation of these methods on complex engineered systems. Dynamics of these systems play a crucial role in design and operations. Hence, it would be advantageous to learn about the mechanisms that may be driving the complex dynamics of systems. In this work, our research question was aimed at addressing this open question about applicability and usefulness of novel machine learning approach in identifying the governing dynamical equations for engineered systems. We focused on distillation column which is an ubiquitous unit operation in chemical engineering and demonstrates complex dynamics i.e. it's dynamics is a combination of heuristics and fundamental physical laws. We tested the method of Sparse Identification of Non-Linear Dynamics (SINDy) because of it's ability to produce white-box models with terms that can be used for physical interpretation of dynamics. Time series data for dynamics was generated from simulation of distillation column using ASPEN Dynamics. One promising result was reduction of number of equations for dynamic simulation from 1000s in ASPEN to only 13 - one for each state variable. Prediction accuracy was high on the test data from system within the perturbation range, however outside perturbation range equations did not perform well. In terms of physical law extraction, some terms were interpretable as related to Fick's law of diffusion (with concentration terms) and Henry's law (with ratio of concentration and pressure terms). While some terms were interpretable, we conclude that more research is needed on combining engineering systems with machine learning approach to improve understanding of governing laws for unknown dynamics.

Prediction of toxicity levels of chemical compounds is an important issue in Quantitative Structure-Activity Relationship (QSAR) modeling. Although toxicity prediction has achieved significant progress in recent times through deep learning, prediction accuracy levels obtained by even very recent methods are not yet very high. We propose a multimodal deep learning method using multiple heterogeneous neural network types and data representations. We represent chemical compounds by strings, images, and numerical features. We train fully connected, convolutional, and recurrent neural networks and their ensembles. Each data representation or neural network type has its own strengths and weaknesses. Our motivation is to obtain a collective performance that could go beyond individual performance of each data representation or each neural network type. On a standard toxicity benchmark, our proposed method obtains significantly better accuracy levels than that by the state-of-the-art toxicity prediction methods.

This paper presents approaches to determine a network based pricing for 3D printing services in the context of a two-sided manufacturing-as-a-service marketplace. The intent is to provide cost analytics to enable service bureaus to better compete in the market by moving away from setting ad-hoc and subjective prices. A data mining approach with machine learning methods is used to estimate a price range based on the profile characteristics of 3D printing service suppliers. The model considers factors such as supplier experience, supplier capabilities, customer reviews and ratings from past orders, and scale of operations among others to estimate a price range for suppliers' services. Data was gathered from existing marketplace websites, which was then used to train and test the model. The model demonstrates an accuracy of 65% for US based suppliers and 59% for Europe based suppliers to classify a supplier's 3D Printer listing in one of the seven price categories. The improvement over baseline accuracy of 25% demonstrates that machine learning based methods are promising for network based pricing in manufacturing marketplaces. Conventional methodologies for pricing services through activity based costing are inefficient in strategically pricing 3D printing service offering in a connected marketplace. As opposed to arbitrarily determining prices, this work proposes an approach to determine prices through data mining methods to estimate competitive prices. Such tools can be built into online marketplaces to help independent service bureaus to determine service price rates.

Metamaterials are artificial materials engineered to have properties not found in naturally occurring materials, and they are best known as materials for invisibility cloaks often featured in sci-fi novels or games. By precisely designing artificial atoms smaller than the wavelength of light, and by controlling the polarization and spin of light, researchers achieve new optical properties that are not found in nature. However, the current process requires much trial and error to find the right material. Such efforts are time-consuming and inefficient; artificial intelligence (AI) could provide a solution for this problem. The research group of Prof. Junsuk Rho, Sunae So and Jungho Mun of Department of Mechanical Engineering and Department of Chemical Engineering at POSTECH have developed a design with a higher degree of freedom that allows researchers to choose materials and design photonic structures arbitrarily by using deep learning.