Search results

Long-term forecasts about commodity market indicators play an important role in informing policy and investment decisions by governments and market participants. Our study examines whether the accuracy of the multi-step forecasts can be improved using deep learning methods.

We first formulate a supervised learning problem and set benchmarks for forecast accuracy using traditional econometric models. We then train a set of deep neural networks and measure their performance against the benchmark.

We find that while the United States Department of Agriculture (USDA) baseline projections perform better for shorter forecast horizons, the performance of the deep neural networks improves for longer horizons. The findings may inform future revisions of the forecasting process.

This study demonstrates an application of deep learning methods to multi-horizon forecasts of agri-cultural commodities, which is a departure from the current methods used in producing these types of forecasts.

The study was aimed to compare the effect of three drying techniques viz., spray, freeze and hot air oven (HAO) drying on yield, nutritional parameters, minerals and physicochemical and morphological characterization of wild banana pulp (Musa balbisiana Colla).

Contents of carbohydrate was estimated by Anthrone reagent, protein by Kjeldahl, fat by Soxhlet, dietary fiber and ash by Association of Official Analytical Chemists (AOAC), minerals by Atomic Absorption Spectrophotometry, gross calorific value by Bomb calorimeter, moisture by moisture analyzer, water activity by water activity meter, morphological characterization by Scanning Electron Microscopy (SEM), statistical level of significance at p < 0.05 by ANOVA, predictive modeling by simple and multiple linear regression.

Freeze and HAO drying were standardized with matured (stage 2) and spray drying with ripe bananas (stage 6). Freeze drying showed highest yield (76.69 ± 0.15%), minerals viz., K (1175.67 ± 1.41), Fe (2.27 ± 0.09), Mg (120.33 ± 0.47), Mn (4.40 ± 0.28) mg/100 g, protein (7.53 ± 0.14%), lesser moisture (7.95 ± 0.01%), water activity (0.17 ± 0.02a_w), hygroscopicity (6.37 ± 1.09%), well dispersed particles by SEM. HAO drying exhibited highest dietary fiber (18.95 ± 0.24%), gross calorific value 357.17 kcal/100 gm, higher solubility (47.22 ± 0.86%). Spray drying showed highest carbohydrate (85.29 ± 0.01%), lowest yield (28.26 ± 0.32%), required 30.5% adjuncts.

Effect of three drying techniques and use of adjuncts were not uniform for ripe and matured bananas.

Commercial utilization of seeded wild banana.

Value addition of wild banana in Assam, India

Freeze drying of mature wild banana pulp (M. balbisiana) was found as best technique utilizing lesser energy.