Naoyuki Hashimoto

Dr. Naoyuki Hashimoto

Kōchi University, Kōchi, Japan
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 May 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MMMd Suruj Mia
Md Suruj Mia
RTRyoya Tanabe
Ryoya Tanabe
LHLuthfan Nur Habibi
Luthfan Nur Habibi
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
Koki HommaKoki Homma
Koki Homma
TTTakashi Tanaka
Takashi Tanaka
Precise yield predictions are useful for implementing precision agriculture technologies and making better decisions in crop management. Convolutional neural networks (CNNs) have recently been used to predict crop yields in unmanned aerial vehicle (UAV)-based remote sensing studies, but weather data have not been considered in modeling. The aim of this study was to explore the potential of multimodal deep learning on rice yield prediction accuracy using UAV multispectral images at the heading stage, along with weather data. The effects of the CNN architectures, layer depths, and weather data integration methods on the prediction accuracy were evaluated. Overall, the multimodal deep learning model integrating UAV-based multispectral imagery and weather data had the potential to develop more precise rice yield predictions. The best models were those trained with weekly weather data. A simple CNN feature extractor for UAV-based multispectral image input data might be sufficient to predict crop yields accurately. However, the spatial patterns of the predicted yield maps differed from model to model, although the prediction accuracy was almost the same. The results indicated that not only the prediction accuracies, but also the robustness of within-field yield predictions, should be assessed in further studies.

9 October 2023 in Agriengineering
Verified
Journal Article
Open access
PDF file
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
YSYuki Saito
Yuki Saito
SYShuhei Yamamoto
Shuhei Yamamoto
TITaro Ishibashi
Taro Ishibashi
RIRuito Ito
Ruito Ito
Koki HommaKoki Homma
Koki Homma
Estimation of rice yield components is required to optimize cultivation management in fields. The leaf area index (LAI) can be a parameter for this estimation, but it has not been evaluated in farmers’ fields. In this study, we analyzed the relationship between the LAI and yield components using data collected over a five-year period in farmers’ fields for the cultivar Hitomebore. Leaf area dynamics (LAD) were parameterized by fitting a growth function to the time-series data of LAI measured using a canopy analyzer. The contribution of LAD to yield components was analyzed using multiple regression. The LAIs at five points during the growing season (effective integrated temperatures of 200, 400, 600, 800, and 1000 °Cd) were calculated using the growth function and the relationship between them and the yield components were analyzed using linear regression. The results of the multiple regression analysis showed that all function parameters significantly affected the yield components at the 5% probability level, with the greatest contribution from the LAI. The LAI at effective integrated temperatures of 400 to 600 °Cd significantly affected most of the yield components. However, the correlation coefficients between the LAI and yield components were not high (R = 0.18–0.61). The LAIs at almost all periods significantly affected the grain number per panicle and 1000-grain weight at the 5% probability level. These results suggest that the LAI could be used for monitoring trends in yield components, while further research on the development of accurate estimation methods is needed.

1 March 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
SYShuhei Yamamoto
Shuhei Yamamoto
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
Koki HommaKoki Homma
Koki Homma
Soybean yield largely varies spatially and yearly in farmer fields. Appropriate growth diagnosis is recommended to stabilize the yield. Leaf area index (LAI) is a representative diagnostic item, but an evaluation method of LAI dynamics with growth has not been established. In this study, we utilized a growth function consisting of an exponential function and a power math function. Parameters were derived from the growth function to be analyzed with yield variability. The LAI was measured weekly by a plant canopy analyzer in farmer fields for 4 years. The dynamics were parameterized by fitting the growth function. The relationship between the parameters of LAI dynamics and soybean yield was analyzed. The growth function was well fitted to measured LAI at R2 = 0.82~0.90 and RMSE = 0.54~0.69 m2 m−2. The parameters of the growth function, such as maximum LAI (LAImax) and cumulative temperature at maximum LAI (TLAImax), quantified the spatial and yearly differences in LAI dynamics, partly explaining those in the yield. The growth function utilized in this study is considered a robust method to quantify LAI dynamics and to diagnose soybean production. The quantification of LAI dynamics may help to develop crop growth monitoring with UAVs (Unmanned Aerial Vehicles) remote sensing as a new diagnostic tool.

25 February 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
HJHyunjin Jung
Hyunjin Jung
RTRyosuke Tajima
Ryosuke Tajima
Rongling YeRongling Ye
Rongling Ye
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
YYYANG YI
YANG YI
Koki HommaKoki Homma
Koki Homma
In crop production, which is largely dependent on environmental conditions, various attempts at environmental or social changes have been highlighted, and many field experiments are needed for them. However, since field experiments in agricultural production are constrained by high labor and time consumption, alternative methods to respond to these constraints are required. In this study, to establish a new method for application to field experiments, we proposed the evaluation of the leaf area index (LAI) of all individual plants in an experimental sweetcorn field using an unmanned aerial vehicle (UAV). Small-scale field experiments were conducted over two years. In the first year, the nitrogen fertilizer level was changed, and the plant density and additional nitrogen fertilizer application time were changed in the next year. Three vegetation indices (VIs), namely, the normalized difference vegetation index (NDVI), enhanced vegetation index 2 (EVI2), and simple ratio (SR), were validated to quantify the LAI estimation using a UAV for individual plants. For the evaluation of the individual plants, we used a plant-based method, which created all of the plant buffers based on the points of existing plants and the plant distance. To confirm the impact of the method, we additionally demonstrated the relationship between the LAI and yield, the results of statical analyses, and the difference of the center and the border of the field. Among the three VIs, index SR was found the most promising in the estimation of the LAI of the individual sweetcorn plants, providing the strongest correlation of yield with SR. Because a lot of data were obtained using the plant-based method, the statical differences in the LAI and yield were more easily detected for the plant density and fertilizer treatments. Furthermore, interesting differences between the center and the border of the field were found. These results indicate the availability and impact of plant-based evaluations using UAVs in near future field experiments.

13 February 2023 in Agriengineering
Verified
Journal Article
Open access
PDF file
LZLina Zhang
Lina Zhang
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
YSYuki Saito
Yuki Saito
KOKasumi Obara
Kasumi Obara
TITaro Ishibashi
Taro Ishibashi
Koki HommaKoki Homma
Koki Homma
In present-day Japan, high quality is the first requirement of rice production. To maintain the quality of rice, the prejudgment technique has been proposed to control rice growth or to separately harvest rice depending on its quality. Since the quality of rice is generally indexed by grain protein content, which is strongly affected by nitrogen content of leaves, one of the major prejudgment techniques is based on leaf greenness evaluation (i.e., SPAD value). However, the technique is under research and not popular with the farmers because the reliability of prejudgment is inadequate. In this study, we investigated the leaf SPAD value at different growth stages of different cultivars and with cultivation methods in farmer fields over four years, and we validated the applicability of prejudgment by comparing with the grain protein content. The results showed that the grain protein content was positively correlated with leaf SPAD value at the maturity stage, but correlated weakly with those at the booting, heading, and milking stages. Since the regression coefficients significantly differed depending on the year, cultivar, and planting method, the acquisition of a regression equation for each target is recommended to predict grain protein content more accurately. The validation in this study suggests that the prejudgment of grain protein content just before harvest has generality for several targets and is useful for harvesting rice depending on the quality. The results in this study may contribute to the attempts to evaluate SPAD value and then rice quality by remote sensing.

15 April 2025 in Agriengineering
Verified
Journal Article
Open access
PDF file
Naoyuki HashimotoNaoyuki Hashimoto
Naoyuki Hashimoto
HYHaruki Yamada
Haruki Yamada
SMShiho Matsuoka
Shiho Matsuoka
High temperature-induced rice sterility has become a major issue in Japan; thus, the conditions influencing this sterility must be better understood to identify effective countermeasures. In this study, a random forest-based sterility estimation model was developed using the sterility rate measured via a field survey and satellite images. Applying this model to Nankoku, Japan, we attempted to map fields based on their sterility rates and visualize the spatial distribution of sterility. The results showed that the rate of change in reflectance from the heading stage until an effective accumulated temperature of 350 °C was reached was an effective model variable. Applying this model to map fields where rice sterility occurred from 2022 to 2024 revealed that more than 41% of the fields in Nankoku may have been damaged, suggesting that many fields might be at risk of adverse effects from high temperatures. The 3-year average sterility rate revealed areas with a high concentration of paddies with a low sterility rate, suggesting that investigating the environment and cultivation management techniques in these areas could provide insights to reduce the sterility rate. Moreover, the growth process up to the heading stage may contribute to the increase in the sterility rate. In the future, we plan to conduct a longitudinal survey based on the generated map to further investigate the relationships between cropping type, cultivar, and weather conditions to develop countermeasures.