Although the necessity for hamlet-scale demographic analysis has been repeatedly pointed out, there has been little research due to scarcity of data. The purpose of this paper is twofold: (1) to explore the feasibility of hamlet-scale demographic analysis using the population census and (2) to examine the merger of hamlets from a demographic perspective using a cohort analysis. Thus, we chose the merger of three hamlets in the Fudo district of Joetsu City, Niigata Prefecture, in 2020. The results follow. (1) The population of hamlets after 1965 could be ascertained from censuses by interpreting census enumeration districts as hamlets, but it was not possible to similarly use censuses after 2000. (2) Fudo Elementary School became independent and expanded in the 1950s because of the large population of the cohort born during 1946-1955, i.e. the “independent-school generation.” In the post-2000 era, as a response to the declining birth rates and subsequent closure of elementary schools, there has been a call for this generation to forge a new bond. (3) The population of people aged in their 60s and 70s who serve as district officers peaked in 2015 and has been declining since. In summary, this hamlet merger was conducted by the “independent-school generation” who were old enough to be designated as district officers and had prepared for a future population decline. Future tasks are to examine the life of each of the “independent-school generation” and to improve hamlet-scale demographic analysis considering gender and social mobility trends.

Determining the flowering stage accurately is crucial for successful artificial fertilization. However, visually identifying the stage requires skill and is subjective. To address this, we developed a simple method for determining the developmental stage of female strobili of Pinus thunbergii using deep learning. A classification model was created, and an associated web application was developed, eliminating the dependency on human observation. The process involved several skilled investigators classifying various images of P. thunbergii female strobili into stages I, II, and III. From a total of 3,074 images with unanimous evaluations, we used MobileNetV2's transition learning to construct and evaluate the model. Although the model had a high accuracy rate of 0.974 and an F-score of 0.949, i.e., a balanced evaluation of precision and recall, it failed to predict some images correctly. Specifically, it struggled with images containing small female strobili in relation to the entire screen, as well as images that included unrelated objects. Additionally, it had difficulty with female strobili that were yellowish-green in color. However, despite these limitations, we propose that this tool can be useful for evaluating traits in the field.

Thematic maps, such as forest change and land cover change maps, are generally inaccurate. The assessment of accuracy, defined as the correctness of a map, is critical for understanding the quality and utility of thematic maps. This review shows the fundamental principles in area estimation and accuracy assessment for forest change maps based on three components: sampling design, response design, and analysis, and then reveals the criterion and recommended practices. Several special cases of accuracy assessment are also discussed. A probability sampling design is implemented in the statistically rigorous accuracy assessment to estimate accuracy based on the comparison of a map and reference data. Population error matrix is crucial in assessing the accuracy and estimating area. Further, the use of unbiased or consistent estimators that correspond to the sampling design is critical for deriving accuracy metrics and area estimates with associated uncertainty. Although the fundamental principles of accuracy assessment are well established, methods for addressing issues have also recently been developed. Practitioners are required to choose the optimal protocols to achieve their objectives of the accuracy assessment because no single protocol or approach can completely address all situations.

This study aimed to estimate the tree height and volume based on image data, which are obtained by conversion of the sound generated from hammering a stem using deep learning. We hammered 20 trees 100 times, recorded the hammering sound, and generated the spectrogram, which presented the sound pressure at each frequency for 0.6 s. Data comprising 10,000 images were loaded into a deep learning model. We used the Neural Network Console (NNC) as the deep learning system and the LeNet, which forms a programmed regression layer to an output layer, as the deep learning algorithm. We divided 10,000 images into 5 equal sets, and performed three learning patterns (LP-I, LP-II, and LP-III). LP-I used the four sets as training data and the remainder as test data, LP-II used three trees and LP-III used six trees, which select for each tree from three divisions (large, medium, small), as test data. A performance evaluation of the proposed model was performed using three indicators: mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R²). Each learning pattern provided very good estimates (R² values for each learning pattern for the test data ranged from 0.9192 to 0.9996), except for the height estimate by LP-III (R²＝0.3672). LP-III generated very poor height estimates with a bias and tended to underestimate by > 30 m and overestimate by < 30 m. However, each learning pattern provided a good estimate of the tree volume, generally without any bias. Thus, we found this method to be more effective for estimation of tree volume than tree height.

As the world's forest area continues to decline, China's forest area has consistently increased since the 1980s. In this research, we clarified the driving force behind this by focusing on the socio-economic factors of China. There is much previous research on the relationship between socio-economic factors and forest resources in various countries. However, the methods used for research in this field are mainly panel data analysis, and the results produced using such tests, for example unit roots and cointegrations of time series data, are limited. In this research, we used the time series data for the last 40 years on forest area and socio-economic factors in China, and we used an autoregressive distribution lag (ARDL) model considering the stationarity of variables and the cointegration relationship. Unit root tests show that all variables are either stationary or becoming stationary after the first differencing. The estimation results show that the change rate of GDP per capita has a positive impact on the change rate of forest area in the short-run but a negative impact in the long-run, and that the change rate of rural populations has a negative impact in both the short- and long-run. It was also shown that the change rate of urban population and foreign direct investments in China have a positive impact on forest coverage rates in the short-run.