This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

Every plant is significantly important in tackling climate change, including Makila (Litsea angulata BI) an endemic wood species found in the forest of Moluccas Provinces. Therefore, this research aimed to examine the role of the Makila plant in tackling climate change by measuring biomass content using constructing an allometric equation. The method used was a destructive sampling, where 40 units of Makila plant at the sampling level were felled, and sorted according to root, stem, branch, rating, and leaf segments. Each segment was weighed both at wet and after drying, followed by a classical assumption test in data processing, and the formulation of an allometric equation. The regression model was examined for normality and suitability in predicting independent variables, ensuring there were no issues with multicollinearity, heteroscedasticity, and autocorrelation. The results yielded a multiple linear regression, namely: Y = −1131.146 + 684.799X₁ + 4.276X₂, where Y is biomass, X₁ is the diameter, and X₂ is the tree height. Based on the results of the t-test: variable X₁ partially affected Y while variable X₂ partially had no effect on Y. The F-test indicated that variables X₁ and X₂ jointly affected Y with R Square: 0.919 or 91.9% and the rest was influenced by other unexplored factors. To simplify biomass prediction and field measurement, a regression equation that used only 1 independent variable, namely tree diameter, was used for the experiment. Allometric equation only used 1 variable, Y = −1,084,626 + 675,090X₁, where X₁ = tree diameter, Y = Total biomass with R = 0.957, and R² = 0.915. Considering the potential for time, cost, and energy savings, as well as ease of measurement in the field, the biomass of young Makila trees was simply predicted by measuring the tree diameter and avoiding the height. This method used the strong relationship between biomass, plant diameter, and height to facilitate the estimation of biomass content accurately by entering the results of field measurements.

High-quality development in China requires higher vocational education, scientific and technological innovation, and sustainable economic development. The spatial distribution patterns of these factors show higher levels in the east and coastal areas compared to the west and inland regions, emphasizing the need for coupling coordination with the social economy. This study examines the impact of sustainable economic development on the coupling coordination degree using the spatial Durbin model. The results show a positive promotion and spillover effect, with regional variations. The main factors affecting the difference in coupling coordination are the amount of technology market contracts, fiscal expenditure on science and technology, patent application authorizations, tertiary industry output value, and the number of R&D institutions. According to the grey prediction model, the coupling coordination degree is expected to increase from 2022 to 2025, but achieving primary coordination may still be challenging in some areas. Therefore, strategies that utilize regional characteristics for coordinated development should be developed to improve the level of coupling coordination and create a mutually beneficial environment.

Preserving roads involves regularly evaluating government policy through advanced assessments using vehicles with specialized capabilities and high-resolution scanning technology. However, the cost is often not affordable due to a limited budget. Road surface surveys are highly expected to use low-cost tools and methods capable of being carried out comprehensively. This research aims to create a road damage detection application system by identifying and qualifying precisely the type of damage that occurs using a single CNN to detect objects in real time. Especially for the type of pothole, further analysis is to measure the volume or dimensions of the hole with a LiDAR smartphone. The study area is 38 province’s representative area in Indonesia. This research resulted in the iRodd (intelligent-road damage detection) for detection and classification per type of road damage in real-time object detection. Especially for the type of pothole damage, further analysis is carried out to obtain a damage volume calculation model and 3D visualization. The resulting iRodd model contributes in terms of completion (analyzing the parameters needed to be related to the road damage detection process), accuracy (precision), reliability (the level of reliability has high precision and is still within the limits of cost-effective), correct prediction (four-fifths of all positive objects that should be identified), efficient (object detection models strike a good balance between being able to recognize objects with high precision and being able to capture most objects that would otherwise be detected-high sensitivity), meanwhile, in the calculation of pothole volume, where the precision level is established according to the volume error value, comparing the derived data to the reference data with an average error of 5.35% with an RMSE value of 6.47 mm. The advanced iRodd model with LiDAR smartphone devices can present visualization and precision in efficiently calculating the volume of asphalt damage (potholes).

To achieve sustainable development, detailed planning, control and management of land cover changes that occur naturally or by human caused artificial factors, are essential. Urban managers and planners need a tool that represents them the information accurate, fast and in exact time. In this study, land use changes of 3 periods, 1994-2002, 2002-2009, 2009-2015 and predictions of 2009, 2015 and 2023 were assessed. In this paper, Maximum Likelihood method was used to classify the images, so that after evaluation of accuracy, amount of overall accuracy for images of 2013 was 85.55% and its Kappa coefficient was 80.03%. To predict land use changes, Markov-CA model was used after assessing the accuracy, and the amount of overall accuracy for 2009 was 82.57% and for 2015 was 93.865%. Then web GIS application was designed via map server application and evoked shape files through map file and open layers to browser environment and for design of appearance of website CSS, HTML and JavaScript languages were used. HTML is  responsible for creating the foundation and overall structure of webpage but beautifying and layout design on CSS. 

The purpose of this study is to predict the frequency of mortality from urban traffic injuries for the most vulnerable road users before, during and after the confinement caused by COVID-19 in Santiago de Cali, Colombia. Descriptive statistical methods were applied to the frequency of traffic crash frequency to identify vulnerable road users. Spatial georeferencing was carried out to analyze the distribution of road crashes in the three moments, before, during, and after confinement, subsequently, the behavior of the most vulnerable road users at those three moments was predicted within the framework of the probabilistic random walk. The statistical results showed that the most vulnerable road user was the cyclist, followed by motorcyclist, motorcycle passenger, and pedestrian. Spatial georeferencing between the years 2019 and 2020 showed a change in the behavior of the crash density, while in 2021 a trend like the distribution of 2019 was observed. The predictions of the daily crash frequencies of these road users in the three moments were very close to the reported crash frequency. The predictions were strengthened by considering a descriptive analysis of a range of values that may indicate the possibility of underreporting in cases registered in the city’s official agency. These results provide new elements for policy makers to develop and implement preventive measures, allocate emergency resources, analyze the establishment of policies, plans and strategies aimed at the prevention and control of crashes due to traffic injuries in the face of extraordinary situations such as the COVID-19 pandemic or other similar events.