Remediation aimed at reducing human exposure to groundwater arsenic in West Bengal, one of the regions most impacted by this environmental hazard, are currently largely focussed on reducing arsenic in drinking water. Rice and cooking of rice, however, have also been identified as important or potentially important exposure routes. Quantifying the relative importance of these exposure routes is critically required to inform the prioritisation and selection of remediation strategies. The aim of our study, therefore, was to determine the relative contributions of drinking water, rice and cooking of rice to human exposure in three contrasting areas of West Bengal with different overall levels of exposure to arsenic, viz. high (Bhawangola-I Block, Murshidibad District), moderate (Chakdha Block, Nadia District) and low (Khejuri-I Block, Midnapur District). Arsenic exposure from water was highly variable, median exposures being 0.02 μg/kg/d (Midnapur), 0.77 μg/kg/d (Nadia) and 2.03 μg/kg/d (Murshidabad). In contrast arsenic exposure from cooked rice was relatively uniform, with median exposures being 0.30 μg/kg/d (Midnapur), 0.50 μg/kg/d (Nadia) and 0.84 μg/kg/d (Murshidabad). Cooking rice typically resulted in arsenic exposures of lower magnitude, indeed in Midnapur, median exposure from cooking was slightly negative. Water was the dominant route of exposure in Murshidabad, both water and rice were major exposure routes in Nadia, whereas rice was the dominant exposure route in Midnapur. Notwithstanding the differences in balance of exposure routes, median excess lifetime cancer risk for all the blocks were found to exceed the USEPA regulatory threshold target cancer risk level of 10(-4)-10(-6). The difference in balance of exposure routes indicate a difference in balance of remediation approaches in the three districts.

No abstract

Long short-term memory (LSTM) models based on specialized deep neural network-based architecture have emerged as an important model for forecasting time-series. However, the literature does not provide clear guidelines for design choices, which affect forecasting performance. Such choices include the need for pre-processing techniques such as deseasonalization, ordering of the input data, network size, batch size, and forecasting horizon. We detail this in the context of short-term forecasting of global horizontal irradiance, an accepted proxy for solar energy. Particularly, short-term forecasting is critical because the cloud conditions change at a sub-hourly having large impacts on incident solar radiation. We conduct an empirical investigation based on data from three solar stations from two climatic zones of India over two seasons. From an application perspective, it may be noted that despite the thrust given to solar energy generation in India, the literature contains few instances of robust studies across climatic zones and seasons. The model thus obtained subsequently outperformed three recent benchmark methods based on random forest, recurrent neural network, and LSTM, respectively, in terms of forecasting accuracy. Our findings underscore the importance of considering the temporal order of the data, lack of any discernible benefit from data pre-processing, the effect of making the LSTM model stateful. It is also found that the number of nodes in an LSTM network, as well as batch size, is influenced by the variability of the input data.

In this paper the asymptotic equivalence of the estimated predictor and the optimal predictor of k-dimensional pth order autoregressive process in the stable case with dependent error variables bas been shown. An expression for the mean square error of the estimated predictor has also been derived.

Accurate short-term solar forecasting is challenging due to weather uncertainties associated with cloud movements. Typically, a solar station comprises a single prediction model irrespective of time and cloud condition, which often results in suboptimal performance. In the proposed model, different categories of cloud movement are discovered using K-medoid clustering. To ensure broader variation in cloud movements, neighboring stations were also used that were selected using a dynamic time warping (DTW)-based similarity score. Next, cluster-specific models were constructed. At the prediction time, the current weather condition is first matched with the different weather groups found through clustering, and a cluster-specific model is subsequently chosen. As a result, multiple models are dynamically used for a particular day and solar station, which improves performance over a single site-specific model. The proposed model achieved 19.74% and 59% less normalized root mean square error (NRMSE) and mean rank compared to the benchmarks, respectively, and was validated for nine solar stations across two regions and three climatic zones of India.