Oil palms are currently in high demand, which tend to increase even higher as a source of alternative energy for humans, especially in Southeast Asian countries. This leads to the study that focuses on the height measurement, using an unmanned aerial vehicle (UAV), and age analysis of oil palm trees planted within the experimental plots in order to predict their yield. The methodology described in the paper provides using Canopy Height Model (CHM) for height measurement and prediction of the oil palm yield by multiple linear regression. The results indicated that the errors caused by overlapping age ranges were found in 3 out of 12 experimental plots. Furthermore, the primary factors influencing the oil palm yield prediction included the age (9 years and above) and canopy density (over 41% of the area), while the secondary factors supporting more accuracy included the total plot area, canopy area, and canopy height, with the coefficient of determination or R-squared at 0.98. In this study, we learned that the aforementioned factors could be concluded from the data collected by an UAV, which reduced the time for measuring the height of each tree manually, resulting in more accurate yield prediction.

The objective of this research is to study urban expansion surrounding archaeological attractions by Normalized Difference Built-up Index (NDBI) technique at ancient civilization site of Haripunjaya Kingdom in Mueang Lamphun District, Lamphun Province, Thailand. From the survey area on October 18-20, 2022, the data was collected on important ancient sites that still appear traces around the city of Lamphun. The study found that there are a total of 13 archaeological sites, each of which is classified into 3 categories: 8 Ancient Religious sites, 4 Acient City Wall sites, and 1 Historical site. Then, surveys of urban and built-up land cover found that within the past 20 years, light urban and built-up land, urban areas and buildings with sparse density increased by 534.45%, or about 5 times, appearing around the old city in Nai Mueang sub-district and the area where the main road passes in a corridor pattern. In addition, the medium urban and built-up land area has also grown more than three times. It can be seen that urban expansion direction in the northern and central of the study area is most located in the 5 sub-district areas: Makhuea Chae, Ban Klang, Wiang Yong, Pa Sak, and Nai Mueang. The NDBI analysis revealed that the archaeological attractions that were most affected by urbanization were the Victory Shrine Pagoda. At present, it has become a historical site in the middle of the community area. It is located in the middle of the shopping mall parking lot, and there are buildings surrounding it, causing the archaeological site to be invaded and damaged greatly. The results of this study can be used to effectively manage cultural tourism planning, especially in the ancient civilization sites in Mueang Lamphun District, to be sustainable in the future.

Oil palm is a vital force in driving the energy business. In 2020, Thailand had 9,954.27 sq.km. (around 6,220,799 Rai) of oil palm plantations, ranking third in the world after Indonesia and Malaysia. Ranong has the highest oil palm crop yield per Rai in Thailand. Notwithstanding, it is challenging to classify land use accurately and keep it up to date by using only labor, due to the need for a number of laborers and high labor costs. Moreover, land use/land cover cannot use spectral information classification alone. Nevertheless, machine learning is a popular data estimation technique that enables a system to learn from sample data; however, there are few studies on its use for data fusion techniques in order to classify land use/land cover, especially concerning oil palm. Therefore, we aim to apply machine learning and data fusion to classify land use/land cover, especially for oil palm. After a multicollinearity test of spectral information and ancillary variables, Surface Reflectance (SR) of Blue, Near Infrared, SWIR-1, NDWI, NDVI and LST were selected with a threshold of correlation coefficients. A stepwise stack of six inputs was created. The first stack included only Surface Reflectance (SR) of Blue, Near Infrared and SWIR-1. NDWI, NDVI and LST were added later. ID4 (Surface Reflectance (SR) of Blue, Near Infrared, SWIR-1, NDWI, NDVI and LST) in the random forest model resulted in OA being 0.9341 and KC being 0.9239, which was the highest among 12 models. ID4 in the random forest model provided the classification results for oil palm very close to the factual number per the figure of 2.90 sq.km (around 1,814 Rai) from the Department of Land.