This paper aims to develop the long short-term memory (LSTM) network modelling strategy based on deep learning principles, tailored for the very short-term, near-real-time global solar radiation (GSR) forecasting. To build the prescribed LSTM model, the partial autocorrelation function is applied to the high resolution, 1 min scaled solar radiation dataset that generates statistically significant lagged predictor variables describing the antecedent behaviour of GSR. The LSTM algorithm is adopted to capture the short- and the long-term dependencies within the GSR data series patterns to accurately predict the future GSR at 1, 5, 10, 15, and 30 min forecasting horizons. This objective model is benchmarked at a solar energy resource rich study site (Bac-Ninh, Vietnam) against the competing counterpart methods employing other deep learning, a statistical model, a single hidden layer and a machine learning-based model. The LSTM model generates satisfactory predictions at multiple-time step horizons, achieving a correlation coefficient exceeding 0.90, outperforming all of the counterparts. In accordance with robust statistical metrics and visual analysis of all tested data, the study ascertains the practicality of the proposed LSTM approach to generate reliable GSR forecasts. The Diebold–Mariano statistic test also shows LSTM outperforms the counterparts in most cases. The study confirms the practical utility of LSTM in renewable energy studies, and broadly in energy-monitoring devices tailored for other energy variables (e.g., hydro and wind energy).

Climate variability, climate change, and extreme events can compound the vulnerability of people heavily reliant on agriculture. Those with intersecting disadvantages, such as women, the poor, and ethnic minority groups, may be particularly affected. Understanding and assessing diverse vulnerabilities, especially those related to ethnicity, are therefore potentially important to the development of policies and programs aimed at enabling adaptation in such groups. This study uses a livelihood vulnerability index (LVI) method, along with qualitative data analysis, to compare the vulnerability of different smallholder farmers in Son La province, one of the poorest provinces in Vietnam. Data were collected from 240 households, representing four minority ethnic groups. The results indicated that household vulnerability is influenced by factors such as income diversity, debt, organizational membership, support from and awareness by local authorities, access to health services, water resources, and location. Results revealed that two of the ethnic groups’ households were, on average, more vulnerable, particularly regarding livelihood strategies, health, water, housing and productive land, and social network items when compared to the other two ethnic groups. The study shows the need for targeted interventions to reduce the vulnerability of these and similarly placed small ethnic communities.