Unmanned aerial vehicles (UAVs or drones) are a very promising branch of technology, and they have been utilized in agriculture—in cooperation with image processing technologies—for phenotyping and vigor diagnosis. One of the problems in the utilization of UAVs for agricultural purposes is the limitation in flight time. It is necessary to fly at a high altitude to capture the maximum number of plants in the limited time available, but this reduces the spatial resolution of the captured images. In this study, we applied a super-resolution method to the low-resolution images of tomato diseases to recover detailed appearances, such as lesions on plant organs. We also conducted disease classification using high-resolution, low-resolution, and super-resolution images to evaluate the effectiveness of super-resolution methods in disease classification. Our results indicated that the super-resolution method outperformed conventional image scaling methods in spatial resolution enhancement of tomato disease images. The results of disease classification showed that the accuracy attained was also better by a large margin with super-resolution images than with low-resolution images. These results indicated that our approach not only recovered the information lost in low-resolution images, but also exerted a beneficial influence on further image analysis. The proposed approach will accelerate image-based phenotyping and vigor diagnosis in the field, because it not only saves time to capture images of a crop in a cultivation field but also secures the accuracy of these images for further analysis.

The measurement of air temperature is strongly influenced by environmental factors such as solar radiation, humidity, wind speed and rainfall. This is problematic in low-cost air temperature sensors, which lack a radiation shield or a forced aspiration system, exposing them to direct sunlight and condensation. In this study, we developed a machine learning-based calibration method for air temperature measurement by a low-cost sensor. An artificial neural network (ANN) was used to balance the effect of multiple environmental factors on the measurements. Data were collected over 305 days, at three different locations in Japan, and used to evaluate the performance of the approach. Data collected at the same location and at different locations were used for training and testing, and the former was also used for k-fold cross-validation, demonstrating an average improvement in mean absolute error (MAE) from 1.62 to 0.67 by applying our method. Some calibration failures were noted, due to abrupt changes in environmental conditions such as solar radiation or rainfall. The MAE was shown to decrease even when the data collected in different nearby locations were used for training and testing. However, the results also showed that negative effects arose when data obtained from widely-separated locations were used, because of the significant environmental differences between them.

Convolutional neural networks (CNNs) can not only classify images but can also generate key features, e.g., the Google neural network that learned to identify cats by simply watching YouTube videos, for the classification. In this paper, crop models are distilled by CNN to evaluate the ability of deep learning to identify the plant physiology knowledge behind such crop models simply by learning. Due to difficulty in collecting big data on crop growth, a crop model was used to generate datasets. The generated datasets were fed into CNN for distillation of the crop model. The models trained by CNN were evaluated by the visualization of saliency maps. In this study, three saliency maps were calculated using all datasets (case 1) and using datasets with spikelet sterility due to either high temperature at anthesis (case 2) or cool summer damage (case 3). The results of case 1 indicated that CNN determined the developmental index of paddy rice, which was implemented in the crop model, simply by learning. Moreover, CNN identified the important individual environmental factors affecting the grain yield. Although CNN had no prior knowledge of spikelet sterility, cases 2 and 3 indicated that CNN realized about paddy rice becoming sensitive to daily mean and maximum temperatures during specific periods. Such deep learning approaches can be used to accelerate the understanding of crop models and make the models more portable. Moreover, the results indicated that CNN can be used to develop new plant physiology theories simply by learning.

Rational water and fertilizer management approaches and technologies could improve water use efficiency and fertilizer use efficiency in paddy rice cultivation. A promising water-conserving technology for paddy rice farming is the alternate wetting and drying irrigation system, established by the International Rice Research Institute. However, the strategy has still not been widely adopted, because water level measurement is challenging work and sometimes leads to a decrease in the rice yield. For the easy implementation of alternate wetting and drying among farmers, we analyzed a dataset obtained from a farmer’s water management study carried out over a three-year period with three cropping seasons at six locations (n = 82) in An Giang Province, Southern Vietnam. We observed a significant relationship between specific water level management and the rice yield and greenhouse gas emissions during different growth periods. The average water level during the crop period was an important factor in increasing the rice yield and reducing greenhouse gas emissions. The average water level at 2 days after nitrogen fertilization also showed a potential to increase the rice yield. The greenhouse gas emissions were reduced when the number of days of non-flooded soil use was increased by 1 day during the crop period. The results offer insights demonstrating that farmers’ implementation of multiple drainage during whole crop period and nitrogen fertilization period has the potential to contribute to both the rice yield increase and reduction in greenhouse gas emissions from rice cultivation.