We compare the long-horizon forecast performance of traditional econometric models with machine learning methods (Neural Networks and Random Forests) for the main energy commodities in the world using monthly prices provided by the International Monetary Fund (IMF). We study the case of Oil (Brent, WTI and Dubai Fateh), Coal (AU) and Gas (US and Russia). Models accuracy are measured using RMSE and MAPE and the M-DM test is applied to evaluate whether there is a statistically significant difference between the methods. We computed thousands of tests regarding the machine learning parameters combinations as there is no method to set the optimal structure for these models. The results show that machine learning methods outperform traditional econometric methods and also that they present an additional advantage, which is the capacity to predict turning points. This study adds further evidence for the discussion on the use of machine learning algorithms for the development of more accurate forecasts to support policymakers and help the decision-making process in the international energy market.

The impact of climate change on agriculture has been one of the most discussed topics in the literature on climate change. Multi-regional computable general equilibrium (CGE) models have frequently been used to examine the impact of climate change on agriculture. However, these studies do not focus on country-specific issues related to the link between climate change and agriculture. This paper aims to address this gap by investigating the economy-wide impacts of climate change on Nepalese agriculture. Nepal makes an interesting case study as it has one of the most vulnerable agricultural economies in South Asia. This paper develops a comparative static multi-household CGE model to trace the direct and indirect impacts of climate change in Nepal. The results suggest that climate change has a significant negative impact on the overall Nepalese economy due to the induced loss of agricultural productivity. The results further reveal that rural households in Nepal, whose livelihoods primarily depend on subsistence farming, will face additional climate change-induced stresses due to already overstrained poverty and a weak social welfare system. The results indicate an urgent need to mainstream adaptation strategies to lessen the negative impacts of any climate change-induced loss of agricultural productivity in Nepal.

No abstract

This paper investigates the feasibility of changes in cropland-use as an adaptation strategy to minimise the economy-wide costs of climate change on agriculture. Nepal makes an interesting case study as it is one of the most vulnerable agricultural economies within South Asia. We develop a comparative static multi-household computable general equilibrium (CGE) model for Nepal, with a nested set of constant elasticity of transformation (CET) functional forms, to model the allocation of land within different agricultural sectors. Land transformation elasticities in these CET functions are allowed to reflect the ease of switching from one crop to another based on their agronomic characteristics. The results suggest that, in the long run, farmers in Nepal tend to allocate land to crops that are comparatively less impacted by climate change, such as paddy, thereby minimising the economy-wide impacts of climate change. Furthermore, the results reveal that land-use change tends to reduce the income disparity between different household groups by significantly moderating the income losses of marginal farmers. Therefore, it is suggested that policy makers in Nepal should prioritise schemes such as providing climatesmart paddy varieties (i.e., those that are resistant to heat, drought and floods) to farmers, subsidising fertilizers, improving agronomic practices, and educating farmers to switch from crops that are highly impacted by climate change to those that are not, such as paddy.

No abstract