| 000 -LEADER |
|---|
| fixed length control field |
03049nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Munir, Safdar |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Long-Term Temperature Forecasting using Deep Learning and Extreme Indices Computation / |
| Statement of responsibility, etc. |
Safdar Munir |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE |
|---|
| Place of production, publication, distribution, manufacture |
Islamabad : |
| Name of producer, publisher, distributor, manufacturer |
SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice |
2025. |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
105p. |
| Other physical details |
Soft Copy |
| Dimensions |
30cm |
| 500 ## - GENERAL NOTE |
|---|
| General note |
Climate change has intensified the demand for accurate long-term temperature forecasting,<br/>particularly in highly vulnerable regions such as Pakistan, where rising temperatures and<br/>extreme events threaten agriculture, water security, public health, and infrastructure.<br/>Conventional climate models, including General Circulation Models (GCMs) and Regional<br/>Climate Models (RCMs), provide essential large-scale projections but face constraints in<br/>spatial resolution, computational cost, and applicability in data-scarce contexts. Recent<br/>advances in deep learning offer powerful alternatives, capable of capturing complex nonlinear relationships and producing high-resolution forecasts that can also inform the<br/>computation of extreme climate indices. This study integrates DL based forecasting with<br/>extreme temperature index computation to generate actionable insights for adaptation<br/>planning in Major Cities of Pakistan. Daily temperature data from the EC-EARTH3-VEG<br/>climate model (converted to °C) were bias-corrected using quantile mapping under two<br/>Shared Socioeconomic Pathways (SSP4.8 and SSP5.85). After data preprocessing multiple<br/>deep learning models LSTM, CNN-LSTM, Transformer, Transformer XL and Deep<br/>Ensemble with Monte Carlo (MC) Dropout, were trained on 1980–2040 data and evaluated<br/>for 2040–2050 and then forecasted till 2100. Model was assessed using MAE, RMSE, R²<br/>with MC dropout. Deep Ensemble outperformed all the single model (MAE = 0.4588;<br/>RMSE = 0.751; R² = 0.992). Projections indicate a Tmax rise of ~2–4 °C and Tmin rise of<br/>~1.5–3 °C by 2100. According to extreme climates indices calculation there continue to be<br/>increases in warming, especially with regards to more heat waves that last longer in<br/>addition to increases in the number of hot days and warm nights as well as fewer frost days.<br/>The warming of nights more than the warming of days, closing the diurnal temperature<br/>range. There is also more total precipitation which is distributed in a growing number of<br/>days, and longer periods of rain which means that heavier rains are becoming less common,<br/>which indicates the beginnings of a warmer, more humid, but drier and stressed climate.<br/>The study highlights that DL Ensemble frameworks can deliver robust, long term<br/>temperature projections and calculation of extreme indices for 25 major cities of Pakistan<br/>and for sake of brevity only data of Lahore, Karachi, Quetta and Gilgit city shown in paper<br/>reset are in appendix. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Supervisor : Dr. Zaib Ali |
| 856 ## - ELECTRONIC LOCATION AND ACCESS |
|---|
| Uniform Resource Identifier |
<a href="http://10.250.8.41:8080/xmlui/handle/123456789/55218">http://10.250.8.41:8080/xmlui/handle/123456789/55218</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
|
| Koha item type |
Thesis |
