An integrated multiple layer perceptron-genetic algorithm decision support system for photovoltaic power plant site selection

There is a need for non-renewable energy sources in generation of power for almost every domestic and commercial purposes. This source of energy helps in the development of a country. Because of the increasing usage of the fossil fuels and depletion of these resources, our focus has been shifted towards the renewable sources of energy like solar, water and wind. Therefore, in the present scenario, the usage of renewable sources has been increasing rapidly. Selection of a solar power plant (SPP) requires environmental factor, local terrain, and local weather issues. Thus, a large amount of investment is required for installation. Multi-criteria decision making (MCDM) is a method that identifies one in choosing the best sites among the other proposed options. This paper gives a detailed study of optimal ranking of SPP site using analytical hierarchy process (AHP), multiple layer perceptron (MLP) neural network trained with back propagation (BP) algorithm and genetic algorithm (GA). Three SPP sites of India were considered and various important criteria like local weather, geographical location, and environmental factors are included in our study as SPP site selection is a multi-criteria problem. A precise comparison of these three methods is listed in this paper.

Constructing a multiple-layer interactome for SARS-CoV-2 in the context of lung disease: Linking the virus with human genes and co-infecting microbes

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has caused millions of deaths worldwide. Many efforts have focused on unraveling the mechanism of the viral infection to develop effective strategies for treatment and prevention. Previous studies have provided some clarity on the protein-protein interaction linkages occurring during the life cycle of viral infection; however, we lack a complete understanding of the full interactome, comprising human miRNAs and protein-coding genes and co-infecting microbes. To comprehensively determine this, we developed a statistical modeling method using latent Dirichlet allocation (called MLCrosstalk, for multiple-layer crosstalk) to fuse many types of data to construct the full interactome of SARS-CoV-2. Specifically, MLCrosstalk is able to integrate samples with multiple layers of information (e.g., miRNA and microbes), enforce a consistent topic distribution on all data types, and infer individual-level linkages (i.e., differing between patients). We also implement a secondary refinement with network propagation to allow our microbe-gene linkages to address larger network structures (e.g., pathways). Using MLCrosstalk, we generated a list of genes and microbes linked to SARS-CoV-2. Interestingly, we found that two of the identified microbes, Rothia mucilaginosa and Prevotella melaninogenica, show distinct patterns representing synergistic and antagonistic relationships with the virus, respectively. We also identified several SARS-COV-2-associated pathways, including the VEGFA-VEGFR2 and immune response pathways, which may provide potential targets for drug design.

Temporal and vertical distributions of the occurrence of the cirrus clouds over the coastal station in the Indian monsoon region

Knowledge of the spatiotemporal coverage of the cirrus clouds is vital in quantifying the radiation budget of the earth-atmosphere system. In this paper, we present the diurnal and vertical distributions of the occurrence of the cirrus clouds during different seasons as well as its interannual variation over Kattankulathur (12.82° N, 80.04° E), east coast of the Bay of Bengal. The long-term (2016–2018) continuous observations of micropulse lidar (MPL) demonstrate the laminar and descending cirrus clouds that occur either as single or multiple layers. The single-layer cirrus occurrence shows a diurnal pattern with frequent occurrence in the late evening (~30–40 %) while multiple-layer cirrus clouds occurrence and early morning (~10–20 %), respectively. For the diurnal pattern in single layer cirrus cloud occurrences, convective processes dominate during the pre-monsoon, southwest (SW), and northeast (NE) monsoon seasons, while the freeze-drying process is favourable during the winter season. However, both convective and freeze-drying processes are dominant in the diurnal pattern of the multiple-layer cirrus occurrences. The occurrence is maximum (~40 %) during the SW and NE monsoon seasons and minimum (~25 %) during the winter. The vertical distributions indicate that the maximum occurrence is confined within the tropical tropopause layer (TTL) during all the seasons. The cirrus cloud rarely occurs above the tropopause; however, it frequently occurs below the TTL during all the seasons. The vertical extent of the occurrence has broader altitude coverage (~8–17 km) during December–March and June–September while narrower during April–May (~10–17 km) and October–November (~9–15 km). The cirrus clouds occurrence also exhibits interannual variations with higher occurrence during 2016 compared to 2017 and 2018 in association with El Nino Southern Oscillation (ENSO).