This study applies machine learning methods such as Decision Tree (CART) and Random Forest to classify drought intensity based on meteorological data. The goal of the study was to evaluate the effectiveness of these methods for drought classification and their use in water resource management and agriculture. The methodology involved using two machine learning models that analyzed temperature and humidity indicators, as well as wind speed indicators. The models were trained and tested on real meteorological data to assess their accuracy and identify key factors affecting predictions. Results showed that the Random Forest model achieved the highest accuracy of 94.4% when analyzing temperature and humidity indicators, while the Decision Tree (CART) achieved an accuracy of 93.2%. When analyzing wind speed indicators, the models’ accuracies were 91.3% and 93.0%, respectively. Feature importance revealed that atmospheric pressure, temperature at 2 m, and wind speed are key factors influencing drought intensity. One of the study’s limitations was the insufficient amount of data for high drought levels (classes 4 and 5), indicating the need for further data collection. The innovation of this study lies in the integration of various meteorological parameters to build drought classification models, achieving high prediction accuracy. Unlike previous studies, our approach demonstrates that using a wide range of meteorological data can significantly improve drought classification accuracy. Significant findings include the necessity to expand the dataset and integrate additional climatic parameters to improve models and enhance their reliability.

The objective of this study is to explore the relationship between changing weather conditions and tourism demand in Thailand across five selected provinces: Chonburi (Pattaya), Surat Thani, Phuket, Chiang Mai, and Bangkok. The annual data used in this study from 2012 to 2022. The estimation method is threshold regression (TR). The results indicate that weather conditions proxied by the Temperature Humidity Index (THI) significantly affect tourism demand in these five provinces. Specifically, changes in weather conditions, such as an increase in temperature, generally result in a decrease in tourism demand. However, the impact of weather conditions varies according to each province’s unique characteristics or highlights. For example, tourism demand in Bangkok is not significantly affected by weather conditions. In contrast, provinces that rely heavily on maritime tourism, such as Chonburi (Pattaya), Phuket, and Surat Thani, are notably affected by weather conditions. When the THI in each province rises beyond a certain threshold, the demand for tourism in these provinces by foreign tourists decreases significantly. Furthermore, economic factors, particularly tourists’ income, significantly impact tourism demand. An increase in the income of foreign tourists is associated with a decrease in tourism in Pattaya. This trend possibly occurs because higher-income tourists tend to upgrade their travel destinations from Pattaya to more upscale locations such as Phuket or Surat Thani. For Thai tourists, an increase in income leads to a decrease in domestic tourism, as higher incomes enable more frequent international travel, thereby reducing tourism in the five provinces. Additionally, the study found that the availability and convenience of accommodation and food services are critical factors influencing tourism demand in all the provinces studied.

The cultivation of red chili in East Java, Indonesia, has significant economic and social impacts, necessitating proactive supply chain measures. This research aimed to identify priority risk agents, develop effective risk mitigation, and enhance supply chain resilience using the SCOR model, House of Risk, Interpretative Structural Modelling (ISM), and synthesis analysis. Examining 238 respondents—including farmers, collectors, wholesalers, retailers, home-agroindustries, and experts—the findings highlight farmers’ critical role in supply chain resilience despite risks from crop failures, weather fluctuations, and pest infestations. Simultaneous planting led to market oversupply and price drops, but accurate pricing information facilitated quick market adaptation. Wholesalers influenced pricing dynamics and income levels, impacting farmers directly. To improve resilience, three main strategies were developed through ten key elements: proactive strategies (real-time SCM tracking, Weather Early Warning Systems, risk management team formation, and training), resistance strategies (partnerships, chili stock reserves, storage and drying technologies, GAP implementation, post-harvest management, agricultural insurance, and Fair Profit Sharing Agreements), and recovery and growth strategies (flexible distribution channels and customizable distribution centers). Furthermore, the study delves into the mediating and moderating effects between variables within the model. This research not only addresses a knowledge gap but also provides stakeholders with evidence to consider new strategies to enhance red chili supply resilience.

This study updates Pereira and Pereira by revisiting the macroeconomic and budgetary effects of infrastructure investment in Portugal using a dataset from the Portuguese Ministry of the Economy covering 1980–2019, thereby capturing a period of austerity and decreased investment in the 2010s. A vector-autoregressive approach re-estimates the elasticity and marginal product of twelve infrastructure types on private investment, employment, and output. The most significant long-term accumulated effects on output accrue from investments in airports, ports, health, highways, water, and railroads. In contrast, those in municipal roads, electricity and gas, and refineries are statistically insignificant. All statistically significant infrastructure investments pay for themselves over time through additional tax revenues. Compared to the previous study, highways, water, and ports have more than doubled their estimated marginal products due to a significant increase in relative scarcity over the last decade. In addition, our analysis reveals an important shift in the impacts of infrastructure investment, now producing more substantial immediate effects but weaker long-term impacts. This change offers policymakers a powerful tool for short-term economic stimulus and is particularly useful in addressing immediate economic challenges.

Effective harvesting strategies are crucial for maximizing annual catch and ensuring the sustainability of lobster (Homarus americanus) farming. This paper presents a nonlinear objective programming model to optimize harvesting intensity based on lobster life cycle dynamics and harvesting characteristics. We model the population dynamics of 1-4 year-old lobsters using differential equations to account for natural mortality, spawning, and harvesting effects. Solving the model with LINGO 12.0, we determine that the optimal harvesting intensity coefficient is 17.36, which maximizes annual catch to 3.88 × 10¹⁰ grams. Results indicate that maintaining harvesting intensity around this optimal value balances economic benefits and population stability, ensuring sustainable farm operations.

COVID-19 has led to abrupt changes in work norms and practices. Despite receding pandemic restrictions, the popularity of remote or hybrid work has not subsided. As employees around the world continue to call for more flexibility and autonomy in the way they work, human resource leaders must continuously consider and evaluate decisions based on ever-changing sentiment, balancing the interests of employees and employers alike. In this perspective article, we review the current state of work in the Southeast Asian region, focusing on Malaysia, Singapore, Indonesia, the Philippines, and Thailand, and present preliminary results from a region-wide mental health assessment that was conducted in late 2022. We argue for the continuation of hybrid work in the region and elaborate on the mental health risks that come with remote working.