Financial time series analysis is an important research area that can predict various economic indicators such as the foreign currency exchange rate. In this paper, a deep-learning-based model is proposed to forecast the foreign exchange rate. Since the currency market is volatile and susceptible to ongoing social and political events, the proposed model incorporates event sentiments to accurately predict the exchange rate. Moreover, as the currency market is heavily dependent upon highly volatile factors such as gold and crude oil prices, we considered these sensitive factors for exchange rate forecasting. The validity of the model is tested over three currency exchange rates, which are Pak Rupee to US dollar (PKR/USD), British pound sterling to US dollar (GBP/USD), and Hong Kong Dollar to US dollar (HKD/USD). The study also shows the importance of incorporating investor sentiment of local and foreign macro-level events for accurate forecasting of the exchange rate. We processed approximately 5.9 million tweets to extract major events’ sentiment. The results show that this deep-learning-based model is a better predictor of foreign currency exchange rate in comparison with statistical techniques normally employed for prediction. The results present evidence that the exchange rate of all the three countries is more exposed to events happening in the US.

Pakistan is an agriculture-based economy and major proportion of irrigation water for its cultivated lands is abstracted from the Upper Indus Basin (UIB). UIB water supplies are mostly contributed from the high-altitude snow and glacier fields situated in the Hindukush–Karakoram–Himalayan ranges. Any change in the flows of these river catchments due to climate variability may result in the form of catastrophic events like floods and droughts and hence will adversely affect the economy of Pakistan. This study aims to simulate snowmelt runoff in a mountainous sub-catchment (Shyok River basin) of the UIB under climate change scenarios. Snowmelt Runoff Model (SRM) coupled with remotely sensed snow cover product (MOD10A2) is used to simulate the snowmelt runoff under current and future climate scenarios in the study area. The results indicate that (a) SRM has efficiently simulated the flow in Shyok River with average Nash–Sutcliff coefficient value (R²) of 0.8 (0.63–0.93) for all six years (2000–2006) of basin-wide and zone-wise simulations, (b) an increase of 10% (by 2050) and 20% (by 2075) in SCA will result in a flow rise of ∼11% and ∼20%, respectively, and (c) an increase of 1°C (by 2025), 2°C (by 2050), 3°C (by 2075) and 4°C (by 2100) in mean temperature will result in a flow rise of ∼26%, ∼54%, ∼81% and ∼118%, respectively. This study suggests that SRM equipped with remotely sensed snow cover data is an effective tool to estimate snowmelt runoff in high mountain data-scarce environments.

In macroeconomics, decision making is highly sensitive and significantly influences the financial and business world, where the interest rate is a crucial factor. In addition, the interest rate is used by the governments to manage the monetary policy. There is a need to design an efficient algorithm for interest rate prediction. The analysis of the social media sentiment impact on financial decision making is also an open research area. In this study, we deploy a deep learning model for the accurate forecasting of the interest rate for the UK, Turkey, China, Hong Kong, and Mexico. For this purpose, daily data of the interest rate and exchange rate covering the period from Jan 2010 to Oct 2019 is used for all the mentioned countries. We also incorporate the input of the twitter sentiments of six mega-events, namely the US election 2012, Mexican election 2012, Gaza under attack 2014, Hong Kong protest 2014, Refugee Welcome 2015, and Brexit 2016. Our results provide evidence that the error of the deep learning model significantly decreases when event sentiment is incorporated. A notable improvement has been observed in the case of the Hong Kong interest rate, i.e., a 266% decline in the error after incorporating event sentiments as an input in the deep learning model.

The damming of rivers has altered their hydrological regimes. The current study evaluated the impacts of major hydrological interventions of the Zhikong and Pangduo hydropower dams on the Lhasa River, which was exposed in the form of break and change points during the double-mass curve analysis. The coefficient of variability (CV) for the hydro-meteorological variables revealed an enhanced climate change phenomena in the Lhasa River Basin (LRB), where the Lhasa River (LR) discharge varied at a stupendous magnitude from 2000 to 2016. The Mann–Kendall trend and Sen’s slope estimator supported aggravated hydro-meteorological changes in LRB, as the rainfall and LR discharge were found to have been significantly decreasing while temperature was increasing from 2000 to 2016. The Sen’s slope had a largest decrease for LR discharge in relation to the rainfall and temperature, revealing that along with climatic phenomena, additional phenomena are controlling the hydrological regime of the LR. Reservoir functioning in the LR is altering the LR discharge. The Soil and Water Assessment Tool (SWAT) modeling of LR discharge under the reservoir’s influence performed well in terms of coefficient of determination (R²), Nash–Sutcliffe coefficient (NSE), and percent bias (PBIAS). Thus, simulation-based LR discharge could substitute observed LR discharge to help with hydrological data scarcity stress in the LRB. The simulated–observed approach was used to predict future LR discharge for the time span of 2017–2025 using a seasonal AutoRegressive Integrated Moving Average (ARIMA) model. The predicted simulation-based and observation-based discharge were closely correlated and found to decrease from 2017 to 2025. This calls for an efficient water resource planning and management policy for the area. The findings of this study can be applied in similar catchments.

Lhasa River Basin being the socio-economic hotspot of Qinghai-Tibetan Plateau is experiencing an increased hydropower capacity in the form of damming and reservoir construction. The Pangduo hydropower station, commenced in 2013, is one of these developments. Lhasa River discharge is analyzed for spatial variability under the reservoir operation at Pondo and Lhasa gauging station. The Mann–Kendall Trend analysis reveals an increased precipitation and a decreased Lhasa River discharge trend upstream and downstream the reservoir. However, the discharge received at Lhasa gauging station is experiencing a greater decline revealed by Sen’s slope estimator. Soil and Water Assessment Tool (SWAT) modelling of the Lhasa River discharge for both the hydrometric stations from 2008–2016 reveals better simulation results for Pondo hydrometric station in terms of R², NSE and PBIAS values. The modelling results for Pondo station correspond comparatively well to the reservoir operation procedures including water level and inflow despite of data availability constraint. However, the importance of non-simulated processes (e.g., groundwater abstractions) to the accurate prediction of the Lhasa flow regime particularly at the downstream flow gauge is recommended. The study can prove beneficial for local water distribution measures in Lhasa River Basin.