Prediction of Relative Humidity in a High Elevated Basin of Western Karakoram by Using Different Machine Learning Models

Adnan, Muhammad; Adnan, Rana Muhammad; Liu, Shiyin; Saifullah, Muhammad; Latif, Yasir; Iqbal, Mujahid

doi:10.5772/intechopen.98226

Cited by 13 publications

(6 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, accurate weather information and accurate humidity forecasting are frequently essential for warning about natural disasters induced by sudden changes in climatic conditions (Adnan et al. 2021 ). The above discussion emphasizes the urgency of monitoring and predicting relative humidity throughout the year in developing countries like India.…”

Section: Introductionmentioning

confidence: 99%

Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models

Shad

Sharma

Singh

2022

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

Relative humidity plays an important role in climate change and global warming, making it a research area of greater concern in recent decades. The present study attempted to implement seasonal autoregressive moving average (SARIMA) and artificial neural network (ANN) with multilayer perceptron (MLP) models to forecast the monthly relative humidity in Delhi, India during 2017–2025. The average monthly relative humidity data for the period 2000–2016 have been used to carry out the objectives of the proposed study. The forecast trend in relative humidity declines from 2017 to 2025. The accuracy of the models has been measured using root mean squared error (RMSE) and mean absolute error (MAE). The results showed that the SARIMA model provides the forecasted relative humidity with RMSE of 6.04 and MAE of 4.56. On the other hand, MLP model reported the forecasted relative humidity with RMSE of 4.65 and MAE of 3.42. This study concluded that the ANN model was more reliable for predicting relative humidity than SARIMA model. Supplementary Information The online version contains supplementary material available at 10.1007/s40808-022-01385-8.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models

Shad

Sharma

Singh

2022

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

show abstract

“…According to the data record from 1998 to 2012, the maximum relative humidity in the eastern part (Hunza) of the Gilgit River basin varies from 59% (March) to 91% (August) whereas the minimum relative humidity varies from 23% (March) to 52% (December). The basin receives a large number of solar radiation in May (5148 W/m 2 ) and small numbers of solar radiation in December (2563 W/m 2 ) (Adnan et al, 2021). The land-cover classification of the Gilgit River basin is displayed in Supplementary Figure S2.…”

Section: Study Areamentioning

confidence: 99%

Spatiotemporal variations in runoff and runoff components in response to climate change in a glacierized subbasin of the Upper Indus Basin, Pakistan

et al. 2022

Self Cite

View full text Add to dashboard Cite

Change in seasonal snowfall and glaciers ablation control year-to-year variations in streamflows of the Upper Indus Basin (UIB) and hence ultimately impacts the water availability in downstream areas of UIB. This situation calls for an urgent response to study the long-term variations in runoff components in response to climate change. The current study investigates the spatiotemporal variations in runoff and runoff components in response to climate change to the streamflows of the Gilgit River from 1981 to 2020 by using the University of British Columbia Watershed Model (UBC WM). Three statistical indices such as the Nash–Sutcliffe efficiency (NSE), the coefficient of determination (R2), and the correlation coefficient (CC) were used to evaluate the performance of UBC WM in simulating the streamflows against observed streamflows. According to statistical indices, the UBC WM performed fairly well during both calibration (1981–2000: R2 = 0.90, NSE = 0.87, and CC = 0.95) and validation periods (2001–2015: R2 = 0.86, NSE = 0.83, and CC = 0.92). Trend analysis revealed a significant increase in all runoff components with large interannual variations in their relative contributions to streamflows from 1981 to 2020. From 1981 to 2020, the average relative contribution of snowmelt, glacier melt, rainfall-runoff, and baseflow was estimated to be 25%, 46%, 5%, and 24%, respectively to the streamflows of the Gilgit River. Seasonal analysis showed that about 86% of total runoff was contributed to the Gilgit River during the summer season (April–September) while only 14% in the winter season (October–March). Further analysis of runoff at a spatial scale revealed that approximately 76% of the total runoff of Gilgit River is generated between elevations from 3680 to 5348 m while 19% of total runoff is generated at an elevation <3680 m and only 5% at an elevation >5348 m. Moreover, it was observed that groundwater contribution from soil lower zone (i.e., 76%) to streamflows was found greater than soil upper zone (i.e., 24%). The outcomes of this study will help the water resource managers and hydrologists to manage the water resources in downstream areas of the UIB for local consumption, industrial use, and agriculture.

show abstract

“…The main steps of the suggested machine-learning techniques shown in Fig. 4 can be expressed as follows (Adnan et al, 2021):…”

Section: Case Study and Data Preparationmentioning

confidence: 99%

“…A machine learning method was used to estimate RH in the Hunza river basin in Pakistan. It has been determined that the error rates in the results obtained using the method are quite low, and thus the MARS method can be easily used in the estimation of relative humidity (Adnan et al, 2021). Due to its highly complex and non-linear nature, research on relative humidity estimation is limited.…”

Section: Introductionmentioning

confidence: 99%

Daily average relative humidity forecasting with LSTM neural network and ANFIS approaches

Özbek

Ünal

Bilgili

2022

Theor Appl Climatol

View full text Add to dashboard Cite

Because hurricanes, droughts, oods, and heat waves are all important factors in measuring environmental changes, they can all result from changes in atmospheric air temperature and relative humidity (RH). Besides, climate, weather, industry, human health, and plant growth are all affected by RH.Accurately and consistently forecasting RH is a challenge due to its non-linear nature. The present study tried to predict one day ahead of RH in determined provinces from different climatic regions of Turkey (Ankara, Erzurum, Samsun, Diyarbakır, Antalya, and Bilecik) using long short-term memory (LSTM) and adaptive neuro-fuzzy inference system (ANFIS) with fuzzy c-means (FCM) based machine learning models. As evaluation criteria, root mean square error (RMSE), mean absolute error (MAE), and correlation coe cient (R) were employed. The outcomes from the forecasting models were also validated using observed data. During the testing stage, the smallest MAE and RMSE values were discovered to be 5.76% and 7.51%, respectively, in Erzurum province, with an R-value of 0.892 when using the LSTM method.Moreover, the smallest MAE and RMSE values were obtained to be 5.95% and 7.67% respectively, in Erzurum province with an R-value of 0.887 using the ANFIS model according to the hourly RH prediction.The results indicate that both the LSTM and ANFIS approaches performed well in daily RH prediction, with the LSTM and ANFIS approaches producing nearly identical results.

show abstract

Prediction of Relative Humidity in a High Elevated Basin of Western Karakoram by Using Different Machine Learning Models

Cited by 13 publications

References 59 publications

Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models

Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models

Spatiotemporal variations in runoff and runoff components in response to climate change in a glacierized subbasin of the Upper Indus Basin, Pakistan

Daily average relative humidity forecasting with LSTM neural network and ANFIS approaches

Contact Info

Product

Resources

About