For developing countries, scarcity of climatic data is the biggest challenge, and model development with limited meteorological input is of critical importance. In this study, five data intelligent and hybrid metaheuristic machine learning algorithms, namely additive regression (AR), AR-bagging, AR-random subspace (AR-RSS), AR-M5P, and AR-REPTree, were applied to predict monthly mean daily reference evapotranspiration (ET0). For this purpose, climatic data of two meteorological stations located in the semi-arid region of Pakistan were used from the period 1987 to 2016. The climatic dataset includes maximum and minimum temperature (Tmax, Tmin), average relative humidity (RHavg), average wind speed (Ux), and sunshine hours (n). Sensitivity analysis through regression methods was applied to determine effective input climatic parameters for ET0 modeling. The results of performed regression analysis on all input parameters proved that Tmin, RHAvg, Ux, and n were identified as the most influential input parameters at the studied station. From the results, it was revealed that all the selected models predicted ET0 at both stations with greater precision. The AR-REPTree model was located furthest and the AR-M5P model was located nearest to the observed point based on the performing indices at both the selected meteorological stations. The study concluded that under the aforementioned methodological framework, the AR-M5P model can yield higher accuracy in predicting ET0 values, as compared to other selected algorithms.

No abstract

Land use/land cover (LULC) changes are among the most significant human-caused global variations affecting the natural environment and ecosystems. Pakistan’s LULC patterns have undergone huge changes since the 1900s, with no clear mitigation plan. This paper aims to determine LULC and normalized difference vegetation index (NDVI) changes as well as their causes in Pakistan’s Southern Punjab province over four different periods (2000, 2007, 2014, and 2021). Landsat-based images of 30 m × 30 m spatial resolution were used to detect LULC changes, while NDVI dynamics were calculated using Modis Product MOD13Q1 (Tiles: h24 v5, h24 v6) at a resolution of 250 m. The iterative self-organizing (ISO) cluster method (object meta-clustering using the minimal distance center approach) was used to quantify the LULC changes in this research because of its straightforward approach that requires minimal human intervention. The accuracy assessment and the Kappa coefficient were calculated to assess the efficacy of results derived from LULC changes. Our findings revealed considerable changes in settlements, forests, and barren land in Southern Punjab. Compared to 2000, while forest cover had reduced by 31.03%, settlement had increased by 14.52% in 2021. Similarly, forest land had rapidly been converted into barren land. For example, barren land had increased by 12.87% in 2021 compared to 2000. The analysis showed that forests were reduced by 31.03%, while settlements and barren land increased by 14.52% and 12.87%, respectively, over the twenty year period in Southern Punjab. The forest area had decreased to 4.36% by 2021. It shows that 31.03% of forest land had been converted to urban land, barren ground, and farmland. Land that was formerly utilized for vegetation had been converted into urban land due to the expansion of infrastructure and the commercial sector in Southern Punjab. Consequently, proper monitoring of LULC changes is required. Furthermore, relevant agencies, governments, and policymakers must focus on land management development. Finally, the current study provides an overall scenario of how LULC trends are evolving over the study region, which aids in land use planning and management.

One of the most important parts of the hydrological cycle is evapotranspiration (ET). Accurate estimates of ET in irrigated regions are critical to the planning, control, and regulation of agricultural natural resources. Accurate ET estimation is necessary for agricultural irrigation scheduling. ET is a nonlinear and complex process that cannot be calculated directly. Reference evapotranspiration (RET) and potential evapotranspiration (PET) are two primary forms of ET. The ideas, equations, and application areas for PET and RET are different. These two terms have been confused and used interchangeably by researchers. Therefore, terminology clarification is necessary to ensure their proper use. The research indicates that PET and RET concepts have a long and distinguished history. Thornthwaite devised the original PET idea, and it has been used ever since, although with several improvements. The development of RET, although initially confused with that of PET, was formally defined as a standard method. In this study, the Preferred Reporting Item for Systematic reviews and Meta-Analysis (PRISMA) was used. Equations for RET estimation were retrieved from 44 research articles, and equations for PET estimation were collected from 26 studies. Both the PET and RET equations were divided into three distinct categories: temperature-based, radiation-based, and combination-based. The results show that, among temperature-based equations for PET, Thornthwaite's (1948) equation was mentioned in 12,117 publications, whereas among temperature-based equations for RET, Hargreaves and Samani's (1985) equation was quoted in 3859 studies. Similarly, Priestley (1972) had the most highly cited equation in radiation-based PET equations (about 6379), whereas Ritchie (1972) had the most highly cited RET equations (around 2382) in radiation-based equations. Additionally, among combination-based PET equations, Penman and Monteith's (1948) equations were cited in 9307 research studies, but the equations of Allen et al. (1998) were the subject of a significant number of citations from 23,000 publications. Based on application, PET is most often applied in the fields of hydrology, meteorology, and climatology, whereas RET is more frequently utilized in the fields of agronomy, agriculture, irrigation, and ecology. PET has been used to derive drought indices, whereas RET has been employed for single crop and dual crop coefficient approaches. This work examines and describes the ideas and methodologies, widely used equations, applications, and advanced approaches associated with PET and RET, and discusses future enhancements to increase the accuracy of ET calculation to attain accurate agricultural irrigation scheduling. The use of advanced tools such as remote sensing and satellite technologies, in addition to machine learning algorithms, will help to improve the accuracy of PET and RET estimates. Researchers will be able to distinguish between PET and RET in the future with the use of the study's results.

Roadway irregularities including vehicle failures, traffic accidents, and more may cause traffic bottlenecks.Targeted traffic management and control depend on precise evaluation of uncommon occurrences' influence range and increasing tendency. It enhances roadway service and operation. Expressway abnormal incidence estimation uses traffic flow theory. Traffic parameter detection accuracy cannot satisfy model input, making engineering application difficult. Emulation analysis was utilized to assess highway traffic flow space-time correlation and vehicle detector features, and VISSIM simulation system was used to calibrate traffic flow parameters and rectify driving behavior parameters. The authors developed a Dynamic-Data-Driven Application Systems (DDDAS)-based highway exceptional event impact area emulation analysis approach after a particle