Traditional methods of cow estrus monitoring technology are not suitable for the current needs of large-scale, intensive and welfare-based farming. There is a need to improve the detection rate of cow estrus and to reduce the emergency response caused by wearing contact devices. Furthermore, it is necessary to verify the practical effectiveness of the LOGISITC and SV (support vector machine) models for modeling cow estrus. In this paper, we have proposed a non-contact cow estrus monitoring method based on the thermal infrared images of cows and have proposed a lab-color-space-based feature extraction method for the thermal infrared images of cow eyes and vulvas. The test subjects were 10 Holstein cows, monitored on a fixed basis, to determine the best segmentation contour. The LOGISTIC and SVM (support vector machine) models were used to establish the cow estrus model using the thermal infrared temperature variation in cows in estrus and cows not in estrus. The experimental results showed that the heat detection rate of the LOGISTIC-based model was 82.37% and the heat detection rate of the SVM-based model was 81.42% under the optimal segmentation profile. The highest temperature in the eye and vulva of cows was the input, and the recall rate was above 86%. The heat monitoring method based on thermal infrared images does not cause stress to cows and meets the needs of modern dairy farming for welfare breeding.

Potato is the fourth largest food crop in the world. Disease is an important factor restricting potato yield. Disease detection based on deep learning has strong advantages in network structure, training speed, detection accuracy, and other aspects. This article took potato leaf diseases (early blight and viral disease) as the research objects, collected disease images to construct a disease dataset, and expanded the dataset through data augmentation methods to improve the quantity and diversity of the dataset. Four classic deep learning networks (VGG16, MobilenetV1, Resnet50, and Vit) were used to train the dataset, and the VGG16 network had the highest accuracy of 97.26%; VGG16 was chosen as the basic research network. A new, improved algorithm, VGG16S, was proposed to solve the problem of large network parameters by using three improvement methods: changing the network structure of the VGG16 network from “convolutional layer + flattening layer + fully connected layer” to “convolutional layer + global average pooling”, integrating CBAM attention mechanism, and introducing Leaky ReLU activation function for learning and training. The improved VGG16S network has a parameter size of 15 M (1/10 of VGG16), and the recognition accuracy of the test set is 97.87%. This article used response surface analysis to optimize hyperparameters, and the test results indicated that VGG16S, after hyperparameter tuning, had further improved its diagnostic performance. At last, this article completed ablation experiments and public dataset testing. The research results will provide a theoretical basis for the timely adoption of corresponding prevention and control measures, improving the yield and quality of potatoes and increasing economic benefits.

Water shortages are the main factor restricting the survival and construction of shelterbelts in sandy areas. Comprehensive analysis of the water balance characteristics of forest stands is crucial for scientifically understanding and regulating the water supply of shelterbelts in sandy areas and formulating appropriate vegetation cultivation and restoration strategies. We simultaneously monitored outer-forest precipitation, canopy interception, stemflow, throughfall, forest transpiration, understory evapotranspiration, and soil moisture content changes in the Salix forest in the Kubuqi Desert during the main growing season (June–October) of 2022. The results showed that the total evapotranspiration of the forest was 185.62 mm, and the components and their proportions of precipitation during the same period were as follows: forest floor evapotranspiration, 94.43 mm (35.88%); stand transpiration, 68.34 mm (25.97%); and canopy interception, 22.85 mm (8.68%). Based on the water balance of the 0–60 cm soil layer and by integrating the changes in soil water storage and the influence of external water transport, the net runoff of the forestland was calculated to be approximately 77.58 mm; that is, the water balance requirements for growth were met. In the future, appropriate irrigation and supplementation can be carried out in June and July to ensure healthier growth in the shelterbelt, and plant photosynthesis and internal physiology can be further studied for cultivation in other desert areas.

Greenhouses, as important parts of facility agriculture, can reduce the restrictions on agricultural production imposed by the natural environment and make rational and efficient use of production resources. We conducted long-term, continuous testing of temperature, humidity, light intensity, and CO₂ concentration parameters in a heliostat greenhouse in the central and western parts of the Inner Mongolia Autonomous Region, a cold and arid region of northern China. A large amount of data was processed by statistical observation, simulation analysis, and 3D reconstruction to obtain the overall distribution, variation pattern, and mathematical model of the regional greenhouse environment in time and space. The results show that the temperature, humidity, light intensity, and CO₂ concentration in the greenhouse have significant daily variation patterns, that there are strong coupling relationships between light intensity–CO₂ concentration–time and indoor temperature–light intensity–CO₂ concentration, that the coefficients of determination (R²) of the mathematical models are 0.88 and 0.89, and that the standard errors (RMSE) are 49.67 ppm and 45.30 ppm, respectively. The environmental parameters were fitted with high accuracy in order to provide scientific data for the cultivation of heliostats in the region.

Amidst climate change, managing water and vegetation adaptability is vital in ecology and agriculture. Salix psammophila is key in deserts, maintaining ecological balance and combating desertification. Understanding its surface condensation and response to weather is critical for survival. This study aims to investigate the formation patterns of surface condensation water under S. psammophila at different irrigation levels and the influence of precipitation, temperature, relative humidity, and wind speed. Conducted in China’s Kubuqi Desert from June to September 2022, the study employed micro-lysimeters with four irrigation test sets and a control group, conducting detailed observations at various locations. The results indicate that S. psammophila significantly influences surface condensation water by blocking solar radiation and reducing wind speed. The drip irrigation system also regulates surface condensation water on S. psammophila. Moreover, meteorological factors such as 24 h maximum temperature, relative humidity difference, wind speed, and air vapor pressure deficit show significant correlations with surface condensation water formation. In conclusion, this study enhances the understanding of desert ecosystem water balance, vegetation adaptability, and efficient water resource utilization. It provides valuable scientific guidance for the conservation and restoration of desert ecosystems.

Mature 5-year-old Prunus domestica trees were used as research objects in plantation areas in arid and semi-arid regions of northern China in Hohhot city; three irrigation gradients and a natural control were set up according to the determination of wilting coefficient and field capacity, and FluorCam 1000-H chlorophyll fluorescence parameters of plant leaves were determined by using a portable chlorophyll fluorescence imager. The results showed that the effects of irrigation gradients on potential photochemical efficiency, maximum photochemical efficiency and non-photochemical burst were not significant (p > 0.05), and the effects on photochemical burst were significant (p < 0.05) at different fertility periods. The potential photochemical efficiency, maximum photochemical efficiency and photochemical burst basically showed a trend of increasing and then decreasing, and the non-photochemical burst showed a trend of decreasing and then increasing during different fertility periods. During the same fertility period, the potential and maximum photochemical efficiencies were significantly increased, and the photochemical and non-photochemical bursts were somewhat reduced under the full irrigation gradient. Therefore, the chlorophyll fluorescence characteristics of Prunus domestica trees at different fertility stages can be regulated by controlling the irrigation gradient to increase the activity of photosystem II (PSII), which in turn improves the photosynthesis of the plants.