More Like this

1. Making machine learning a useful tool in the accelerated discovery of transition metal complexes

   https://doi.org/10.1002/wcms.1439  

   Kulik, Heather_J ( August 2019 , WIREs Computational Molecular Science)

   As machine learning (ML) has matured, it has opened a new frontier in theoretical and computational chemistry by offering the promise of simultaneous paradigm shifts in accuracy and efficiency. Nowhere is this advance more needed, but also more challenging to achieve, than in the discovery of open‐shell transition metal complexes. Here, localizeddorfelectrons exhibit variable bonding that is challenging to capture even with the most computationally demanding methods. Thus, despite great promise, clear obstacles remain in constructing ML models that can supplement or even replace explicit electronic structure calculations. In this article, I outline the recent advances in building ML models in transition metal chemistry, including the ability to approach sub‐kcal/mol accuracy on a range of properties with tailored representations, to discover and enumerate complexes in large chemical spaces, and to reveal opportunities for design through analysis of feature importance. I discuss unique considerations that have been essential to enabling ML in open‐shell transition metal chemistry, including (a) the relationship of data set size/diversity, model complexity, and representation choice, (b) the importance of quantitative assessments of both theory and model domain of applicability, and (c) the need to enable autonomous generation of reliable, large data sets both for ML model training and in active learning or discovery contexts. Finally, I summarize the next steps toward making ML a mainstream tool in the accelerated discovery of transition metal complexes.

   This article is categorized under:

   Electronic Structure Theory > Density Functional Theory

   Software > Molecular Modeling

   Computer and Information Science > Chemoinformatics

    

   more » « less
2. Electrical and Structural Analysis of β ‐Ga 2 O 3 /GaN Wafer‐Bonded Heterojunctions with a ZnO Interlayer

   https://doi.org/10.1002/aelm.202300174  

   Jian, Zhe ; Sun, Kai ; Kosanovic, Stefan ; Clymore, Christopher J. ; Mishra, Umesh ; Ahmadi, Elaheh ( June 2023 , Advanced Electronic Materials)

   Wafer bonding ofβ‐Ga₂O₃and N‐polar GaN single crystal substrates is demonstrated by adding ZnO as a “glue” interlayer. The wafers are fully bonded such that Newton rings are not observed. Temperature‐dependent current‐voltage (I–V) measurements are conducted on the as‐bonded Ga₂O₃/ZnO/N‐polar GaN test structure and after annealing at 600 °C and 1100 °C. The impact of post‐annealing temperature on the electrical and structural characteristics of the bonded samples is investigated. A consistently ohmic‐like characteristic is obtained by annealing the bonded wafers at 1100 °C in N_2,which is in part due to crystallization of ZnO and diffusion of Ga into ZnO which makes it n‐type doped. The wafer bonding ofβ‐Ga₂O₃and GaN achieved in this work is promising to combine the material merits of both GaN and Ga₂O₃targeting breakthrough high‐frequency and high‐power device performances.

    

   more » « less
3. Qualitative inverse problems: mapping data to the features of trajectories and parameter values of an ODE model

   https://doi.org/10.1088/1361-6420/acd414  

   Duan, X. ; Rubin, J. E. ; Swigon, D. ( May 2023 , Inverse Problems)

   Our recent work on linear and affine dynamical systems has laid out a general framework for inferring the parameters of a differential equation model from a discrete set of data points collected from a system being modeled. It introduced a new class of inverse problems where qualitative information about the parameters and the associated dynamics of the system is determined for regions of the data space, rather than just for isolated experiments. Rigorous mathematical results have justified this approach and have identified common features that arise for certain classes of integrable models. In this work we present a thorough numerical investigation that shows that several of these core features extend to a paradigmatic linear-in-parameters model, the Lotka–Volterra (LV) system, which we consider in the conservative case as well as under the addition of terms that perturb the system away from this regime. A central construct for this analysis is a concise representation of parameter and dynamical features in the data space that we call theP_n-diagram, which is particularly useful for visualization of the qualitative dependence of the system dynamics on data for low-dimensional (smalln) systems. Our work also exposes some new properties related to non-uniqueness that arise for these LV systems, with non-uniqueness manifesting as a multi-layered structure in the associatedP₂-diagrams.

    

   more » « less
4. Inferring dolphin population status: using unoccupied aerial systems to quantify age‐structure

   https://doi.org/10.1111/acv.12978  

   Vivier, F. ; Andrés, C. ; Gonzalvo, J. ; Fertitta, K. ; van_Aswegen, M. ; Foroughirad, V. ; Mann, J. ; McEntee, M. ; Wells, R_S ; Bejder, L. ( August 2024 , Animal Conservation)

   Assessing trends in population abundance and demographics is crucial for managing long‐lived and slow‐reproducing species. Obtaining demographic data, and age‐structure information, is challenging, notably for cetaceans. To address this, we combined Unoccupied Aerial System (UAS; drone) photogrammetry data with long‐term (>20 years) photo identification data to assess the age‐structure of the critically endangered sub‐population of common bottlenose dolphins (Tursiops truncatus) of the Gulf of Ambracia, Greece. We compared our findings with two extensively studied non‐endangered bottlenose dolphin populations (T. aduncusin Shark Bay, Australia, andT. truncatusin Sarasota Bay, USA). Using a log‐linear model, we estimated the total body lengths (TL) of 160 known‐aged dolphins between 2021 and 2023 from blowhole‐to‐dorsal‐fin distance (BHDF) measurements collected during surfacing. Subsequently, we tested four growth models to establish an age‐length growth curve. We assessed the sub‐population's age‐structure using three methods: (1) UAS‐derived TL estimates, (2) age‐length growth curve and (3) long‐term monitoring data (i.e. actual age‐structure). UAS‐measured TL (247.6 ± 32.2 cm) and UAS‐estimated TL (246.0 ± 34.7 cm) of the Greek sub‐population showed no differences. The Richards Growth model suggested an asymptotic length of 258.5 cm. In Greece, resulting age‐structure estimates across the three methods revealed no significant differences (P > 0.1). The Gulf of Ambracia and Shark Bay populations shared similar age‐structures, while Sarasota had higher proportions of 2–10 year‐olds and lower proportions of 10+ year‐olds. All populations had a comparable proportion of 0–2 year‐olds (~14%), indicating a similar reproductive rate. Our findings suggest stability in the Greek sub‐population; however, additional monitoring of reproductive parameters is essential before concluding its status. We demonstrated the effectiveness of UAS‐photogrammetry in rapidly quantifying population age‐structure, including scenarios with limited or no demographic data. This technique shows promise for enhancing precision, timeliness, cost‐effectiveness and efficiency in population monitoring and informing timely conservation management decisions.

    

   more » « less
5. A Deep Learning Based Approach to Predict Sequential Design Decisions

   https://doi.org/10.1115/DETC2019-97625  

   Rahman, Molla Hafizur ; Xie, Charles ; Sha, Zhenghui ( November 2019 , ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference)

   During a design process, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are important to the development of new algorithms embedded with human intelligence to augment computational design. In this paper, we develop a deep learning based approach to model and predict designers’ sequential decisions in a system design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short term memory unit model for deep leaning. This approach is demonstrated in a solar energy system design case study, and its prediction accuracy is evaluated benchmarked on several commonly used models for sequential design decisions, such as Markov Chain model, Hidden Markov Chain model, and random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to reply on both short-term and long-term memory of past design decisions in guiding their decision making in future design process. Our approach is general to be applied in many other design contexts as long as the sequential design action data is available.

    

   more » « less