To investigate the effect of aerated irrigation on the soil environment and yield in the root zone of maize, and to provide a basis for the extension of aerated irrigation, a 2-year experiment (2020–2021) was conducted at the Zhanjiang National Soil Quality Observation Experiment Station, with two experimental observations per year (spring-summer and fall-winter) to investigate the effects of aerated irrigation (AI) and non-aerated irrigation (CK) on soil respiration rate, soil temperature, water content, oxygen content, soil bacterial biomass and root biomass. We used partial least square regression analysis (PLSR) to establish the regression equations of soil respiration rate, soil temperature, water content, oxygen content, soil bacterial biomass and root biomass under the two treatments, and the screening of the main soil environmental factors affecting changes in soil respiration rate under aerated irrigation technology. The results showed that, compared with CK, the AI treatment significantly increased the soil respiration rate and soil oxygen content (15.38~17.87% and 18.94~25.17%, respectively), as well as the root biomass and soil bacterial biomass (14.99~19.09% and 35.10~45.59%, respectively), and reduced the soil water content by 5.33~12.71% (p < 0.05). The effects of different treatments on soil temperature were not significant. The mean fruit yield with AI treatment was also 7.16~20.51% higher (p < 0.05) than that with CK, and the stem thickness and leaf area of maize plants were significantly increased (9.31~17.06% and 8.68~15.20%, respectively (p < 0.05)). The regression fitting results showed that the soil respiration rate is quadratic polynomial negatively correlated with soil temperature, water content and soil oxygen, and the power function is positively correlated with root biomass and bacterial biomass under the two treatments. The variable importance for projection (VIP) values of the PLSR model showed a soil temperature VIP = 1.51, soil oxygen content VIP = 1.42 and root biomass VIP = 1.40, demonstrating that aerated irrigation technology can drive soil respiration rate by changing soil oxygen content and root biomass. Furthermore, the improvements in soil aeration conditions and respiration with AI appeared to facilitate the improvement in fruit yields, which also suggests the economic benefits of AI.

The timing of spray application plays an essential role in daily pesticides management. Proper wind speed, air temperature, and relative humidity are the main external factors to improve the efficacy of pesticides, reduce the amount of spray drift and environmental pollution. Very few previous studies have focused on the need for short-term weather prediction in rapid spraying decisions. In this paper, a Convolutional-LSTM encoder-decoder (ConvLSTM-AE) hybrid model for multivariate output and multi-step prediction with short time intervals is proposed to predict these three agrometeorological variables in advance. This model can predict daily weather conditions at 15-minute intervals and track the changes of time-varying systems effectively. This method was also compared with other methods such as CNN, multi-head CNN, LSTM encoder-decoder, and CNN-LSTM encoder-decoder models. The results show that the proposed model outperforms other models and is suitable for daily weather forecasts in a short time interval. The obtained rapid and accurate prediction results provide a reliable basis for precise spray timing in actual farming.

The agriculture field is one of the most important fields where computational techniques play an imperative role for decision-making whether it is the automation of watering of plants, controlling of humidity levels, and detection of plant diseases and growth of plants. There are problems in the conventional methods where newer computational techniques and image processing methods are not used to keep track of growth of plants. The traditional image capturing and processing models have problems of large image segmentation error, excessive feature extraction time, and poor recognition output. In order to overcome the problems in the traditional plant growth methods based on image processing automations, computer image processing with computational method has been proposed to analyze the plant growth by utilizing state recognition method for corn and rice crops. An image acquisition platform is established on the basis of CMOS image sensor for crop image acquisition. The binary processing is performed, and then the images are segmented to reduce error of segmentation results in the traditional methods. To extract image features of corn and rice crops, convolution neural network (CNN) with newer architecture is used. According to contour information of images, the block wavelet transform method is used for feature adaptive matching. The binary tree structure is used to divide the growth period of corn and rice crops. The fuzzy mathematical model is also devised to identify the characteristics of crops in different growth periods and to complete the identification of growth state. Experimental results show that the proposed method effectively improves problems of traditional methods with better image recognition effect and reduces the time of feature recognition. The time to extract features by the proposed method is 1.4 seconds, whereas comparative methods such as random forest (RF) take 3.8s and other traditional techniques take 4.9s. Segmentation result error of the recognition method is also reduced significantly.

Rhizoctonia solani AG1-IA (Thandfephorus cucumeris teleomorph) is the causative agent of rice sheath blight in Chinese paddy fields. Due to the importance of the disease and the lack of comprehensive information on the genetic structure of the fungus populations, 25 isolates collected from Hubei, Sichuan, Anhui, and Jiangsu provinces, and southern China's Yangtze River basin were examined for morphological characteristics, growth rate, and genetic diversity of this pathogen. The anastomosis group determination test results showed that all isolates belong to the AG1-IA anastomosis group. To quickly diagnose and confirm the anastomosis group of isolates, ten isolates along with AG1-IA and AGA standard isolates were examined by specific primers AG1-IA. A 256bp band was amplified in all of them. The results of the growth velocity study divided the isolates into two groups’ fast growth (68% of isolates) and slow growth (32% of isolates). The genetic diversity of 25 isolates was assessed using the RAPD marker. Among the 20 primers, bands from seven primers ranging from 250 to 5,000bp were performed using the Jaccard similarity coefficient and UPGMA method by data cluster analysis of NTSYS-pc software. The cluster analysis results divided the isolates into two groups with a similarity level of 36%, which corresponded to the grouping of isolates into two groups of fast growth and slow growth. At the level of 80% similarity, the isolates were divided into 23 groups, which indicate the high genetic diversity of these isolates. The results of the molecular analysis showed that isolates belonging to a geographical area do not necessarily have a genetic affinity. This study performed rapid detection of R. solani AG1-IA using specific primers AG1-IA, and evaluation of genetic diversity of rice sheath blight isolates was performed by RAPD marker in this study.