Predicting rainfall is a challenging and critical task due to its significant impact on society. Timely and accurate predictions are essential for minimizing human and financial losses. The dependence of approximately 60% of agricultural land in India on monsoon rainfall implies the crucial nature of accurate rainfall prediction. Precise rainfall forecasts can facilitate early preparedness for disasters associated with heavy rains, enabling the public and government to take necessary precautions. In the North-Western Himalayas, where meteorological data are limited, the need for improved accuracy in traditional modeling methods for rainfall forecasting is pressing. To address this, our study proposes the application of advanced machine learning (ML) algorithms, including random forest (RF), support vector regression (SVR), artificial neural network (ANN), and k-nearest neighbour (KNN) along with various deep learning (DL) algorithms such as long short-term memory (LSTM), bi-directional LSTM, deep LSTM, gated recurrent unit (GRU), and simple recurrent neural network (RNN). These advanced techniques hold the potential to significantly improve the accuracy of rainfall prediction, offering hope for more reliable forecasts. Additionally, time series techniques, including autoregressive integrated moving average (ARIMA) and trigonometric, Box-Cox transform, arma errors, trend, and seasonal components (TBATS), are proposed for predicting rainfall across the altitudinal gradients of India’s North-Western Himalayas. This approach can potentially revolutionise how we approach rainfall forecasting, ushering in a new era of accuracy and reliability. The effectiveness and accuracy of the proposed algorithms were assessed using meteorological data obtained from six weather stations at different elevations spanning from 1980 to 2021. The results indicate that DL methods exhibit the highest accuracy in predicting rainfall, as measured by the root mean squared error (RMSE) and mean absolute error (MAE), followed by ML algorithms and time series techniques. Among the DL algorithms, the accuracy order was bi-directional LSTM, LSTM, RNN, deep LSTM, and GRU. For the ML algorithms, the accuracy order was ANN, KNN, SVR, and RF. These findings suggest that altitude significantly affects the accuracy of the models, highlighting the need for additional weather stations in this mountainous region to enhance the precision of rainfall prediction.

Mushk Budiji-an indigenous aromatic rice variety is usually grown at an altitude ranging from 5000 to 7000 ft above mean sea level in Highland Himalayas. This study was conducted to investigate the effects of altitude, soil nitrogen content and climatic conditions (temperature) of the selected locations on the flavor profile of Mushk Budiji using gas chromatography-mass spectroscopy (GC–MS) and electronic nose (E-nose). E-nose being rapid and non-destructive method was used to validate the results of volatile aromatic compounds obtained using GC–MS in Mushk Budiji. Around 35 aromatic compounds were identified in Mushk Budiji rice samples. Highest volatile peak area percentage (105.41%) was recorded for Mushk Budji grown at an altitude of 5216.53 ft. Highest E-nose score (2.52) was obtained at an altitude of 6299.21 ft. Over-expression of fatty acid degradation and linoleic acid metabolism genes was observed at higher altitudes, whereas lipid biosynthesis was negatively influenced by higher altitude. Fatty acid degradation and linoleic acid metabolism is responsible for the synthesis of volatile aromatic compounds in Mushk Budiji. This study will therefore be the path finder for investigating the intricate mechanism behind the role of altitude on aroma development in Mushk Budiji rice for future studies.

Transplanting rice appears to pose many problems, including depletion of freshwater reservoirs and competition for labor. Conversely, direct seeding allows us to overcome shortcomings associated with conventional transplanting. Nitrogen is a crucial nutrient needed for plant growth and yield. Therefore, this study was executed to analyze the influence of nitrogen on the performance of rice genotypes grown by direct seeding in wet soil. The experiment comprised various rice cultivars, i.e., Shalimar Rice-1, Shalimar Rice-3, Shalimar Rice-4, and Jhelum, and nitrogen (N) levels, i.e., 0, 90, 120, and 150 kg/ha. Shalimar Rice-4 produced a maximum grain yield (6.39 t/ha), followed by Shalimar Rice-3 and Jhelum). The application of 150 kg N/ha showed maximum values for growth parameters, yield attributing traits, and grain yield (6.68 t/ha); however, it remained at par with 120 kg N/ha. Crop water productivity was highest in Shalimar Rice-4 (0.49 kg/m³), and the same showed a consistent increase with increasing N levels from 0–150 kg/ha, with a comparable value of 0.49 to 0.51 recorded at 120 and 150 kg N/ha. Moreover, the Shalimar Rice-1 variety required the maximum in growing degree days (GDD) and helio-thermal units (HTU) to attain different phenological stages till physiological maturity (131 days). However, the cultivar Shalimar rice-4 (SR-4) performed better by registering significantly higher heat use efficiency (HUE) (4.44 kg/ha °C/day). Additionally, the highest net return and the benefit-cost ratio were registered by Shalimar Rice-4. B:C ratio of 1.75 was realized from application of 150 kg N/ha, which remained very close to that achieved with 120 kg N/ha. In conclusion, the rice cultivar Shalimar Rice-4 with the application of 120 kg N/ha could boost rice production under DSR in water-scarce regions of temperate northern India.