Abstract:Groundwater accounts for half of Indian urban water use. However, little is known about its sustainability, because of inadequate monitoring and evaluation. We deployed a dense monitoring network in 154 locations in Bengaluru, India between 2015 and 2017. Groundwater levels collected at these locations were analyzed to understand the behavior of the city's groundwater system. At a local scale, groundwater behavior is non-classical, with valleys showing deeper groundwater than ridge-tops. We hypothesize that this is due to relatively less pumping compared to artificial recharge from leaking pipes and wastewater in the higher, city core areas, than in the rapidly growing, lower peripheral areas, where the converse is true. In the drought year of 2016, groundwater depletion was estimated at 27 mm, or 19 Mm 3 over the study area. The data show that rainfall has the potential to replenish the aquifer. High rainfall during August-September 2017 led to a mean recharge of 67 mm, or 47 Mm 3 for the study area. A rainfall recharge factor of 13.5% was estimated from the data for 2016. Sustainable groundwater management in Bengaluru must account for substantial spatial socio-hydrological heterogeneity. Continuous monitoring at high spatial density will be needed to inform evidence-based policy.

The functional structure of proteins is heavily influenced by their folding behavior. AlphaFold, a powerful artificial intelligence (AI) program trained on information from the Protein Data Bank (PDB), was developed to predict the 3D structure of proteins from its amino acid sequence. Inspired by this, we aim to elucidate structural features of synthetic single-chain polymer nanoparticles (SCNPs) based on compositional information (monomers, chain length, molecular weight, charge, and valency) by machine learning (ML). Specifically, we demonstrate the effectiveness of ML to improve the efficiency of SCNP design and uncover important polymer design attributes to mimic protein-like structural features. To start, we randomly screened over 1000 synthesized SCNPs through a combination of high-throughput dynamic light scattering (DLS) and small-angle X-ray scattering (SAXS) and compared these results to simulated protein data from the PDB. Then, utilizing evidential neural networks (ENets), we predicted, synthesized, and characterized 30 novel compact SCNPs. Incredibly, this data-driven approach yielded 58% of the predicted SCNPs with Porod exponent ≥ 3.5 as opposed to 5% of SCNPs from the random screen. Using Shapely additive explanation (SHAP) values, we further uncovered interesting contributions of monomer content on Porod exponent and radius of gyration. From this work, we have shown that an ML-guided approach proves effective for the challenging, unintuitive problem of nanoparticle design.

No abstract

No abstract

No abstract