As traditional supply chains face increasingly severe environmental issues, and as countries promote green development and sustainable development policy concepts, cultivating green supply chain operation models is gradually coming to be highly valued by governments and enterprises. Generally speaking, the production of green products incurs higher additional costs, and thus, their total production costs also increase. In this work, we studied the coordination mechanism, by considering carbon emissions and product green level dependent demand, in which the product green level is related to the random demand. Under the green supply chain buyback contract with the green product $R\&D$ cost sharing between the manufacturer and the retailer, both the product green level and the order quantity need to be decided, to maximize the channel profit. In order to coordinate the green supply chain, the manufacturer needs to share both the risk of good salvage and the green product $R\&D$ cost with the retailer. We found that both the wholesale price and the buyback price increase in the manufacturer’s proposition of the green product $R\&D$ cost, but decrease in the emission reduction efficiency coefficient or carbon trading price. In addition, the product green level, the optimal order quantity and the channel profit increase in the emission reduction efficiency coefficient, but decrease in the $R\&D$ cost coefficient of the product green level. Interestingly, we found that if the carbon trading price is low, the manufacturer will set a low product green level, and the product carbon emission trading is a cost for the supply chain. The increment of the carbon trading price leads to a higher cost, such that the channel profit is decreased. However, if the carbon trading price is high, the manufacturer will set a high product green level, and the product carbon emission trading is a revenue for the supply chain. The increment of the carbon trading price leads to a higher revenue, such that the channel profit is increased.

Sustainable development coordination can facilitate the new energy vehicles (NEV) supply chain. By a coordinating supply contract, the operating costs can be reduced and supply chain competitiveness can be improved. We designed a revenue-sharing and buy-back (RSBB) contract to coordinate the supply chain with the cash-strapped retailer or manufacturer and analyzed the impact of the acceptable bankruptcy risk and own fund on the optimal order quantity, supply chain profits, and coordinating factors, including revenue share and buy-back price. Interestingly, the revenue share decreases in the acceptable bankruptcy risk, but the buy-back price increases in the acceptable bankruptcy risk when the retailer has financial constraints. However, when the manufacturer has financial constraints, the revenue share increases in the acceptable bankruptcy risk, but the buy-back price decreases in the acceptable bankruptcy risk.

This study proposes a decomposed broad learning model to improve the forecasting accuracy for tourism arrivals on Hainan Island in China. With decomposed broad learning, we predicted monthly tourist arrivals from 12 countries to Hainan Island. We compared the actual tourist arrivals to Hainan from the US with the predicted tourist arrivals using three models (FEWT-BL: fuzzy entropy empirical wavelet transform-based broad learning; BL: broad Learning; BPNN: back propagation neural network). The results indicated that US foreigners had the most arrivals in 12 countries, and FEWT-BL had the best performance in forecasting tourism arrivals. In conclusion, we establish a unique model for accurate tourism forecasting that can facilitate decision-making in tourism management, especially at turning points in time.