Yield Estimation of High-Density Cotton Fields Using Low-Altitude UAV Imaging and Deep Learning

Background: Different from other parts of the world, China has its own cotton planting pattern. Cotton are densely planted in wide-narrow rows to increase yield in Xinjiang, China, causing the difficulty in the accurate evaluation of cotton yields using remote sensing in such field with branches occluded and overlapped. Results: In this study, low-altitude unmanned aerial vehicle (UAV) imaging and deep convolutional neural networks (DCNN) were used to estimate the yields of densely planted cotton. Images of cotton field were acquired by an UAV at the height of 5 m. Cotton bolls were manually harvested and weighted afterwards. Then, a modified DCNN model was developed by applying encoder-decoder recombination and dilated convolution for pixel-wise cotton boll segmentation termed CD-SegNet. Linear regression analysis was employed to build up the relationship between cotton boll pixels ratio and cotton yield. Yield estimations of four cotton fields were verified after machine harvest and weighting. The results showed that CD-SegNet outperformed the other tested models including SegNet, support vector machine (SVM), and random forest (RF). The average error of the estimated yield of the cotton fields was 6.2%. Conclusions: Overall, the yield estimation of densely planted cotton based on lowaltitude UAV imaging is feasible. This study provides a methodological reference for cotton yield estimation in China.

Monitoring Oasis Cotton Fields Expansion in Arid Zones Using the Google Earth Engine: A Case Study in the Ogan-Kucha River Oasis, Xinjiang, China

Rapid and accurate mapping of the spatial distribution of cotton fields is helpful to ensure safe production of cotton fields and the rationalization of land-resource planning. As cotton is an important economic pillar in Xinjiang, accurate and efficient mapping of cotton fields helps the implementation of rural revitalization strategy in Xinjiang region. In this paper, based on the Google Earth Engine cloud computing platform, we use a random forest machine-learning algorithm to classify Landsat 5 and 8 and Sentinel 2 satellite images to obtain the spatial distribution characteristics of cotton fields in 2011, 2015 and 2020 in the Ogan-Kucha River oasis, Xinjiang. Unlike previous studies, the mulching process was considered when using cotton field phenology information as a classification feature. The results show that both Landsat 5, Landsat 8 and Sentinel 2 satellites can successfully classify cotton field information when the mulching process is considered, but Sentinel 2 satellite classification results have the best user accuracy of 0.947. Sentinel 2 images can distinguish some cotton fields from roads well because they have higher spatial resolution than Landsat 8. After the cotton fields were mulched, there was a significant increase in spectral reflectance in the visible, red-edge and near-infrared bands, and a decrease in the short-wave infrared band. The increase in the area of oasis cotton fields and the extensive use of mulched drip-irrigation water saving facilities may lead to a decrease in the groundwater level. Overall, the use of mulch as a phenological feature for classification mapping is a good indicator in cotton-growing areas covered by mulch, and mulch drip irrigation may lead to a decrease in groundwater levels in oases in arid areas.

Plant age, crop stage and surrounding habitats: their impact on sucking pests and predators complex in cotton (Gossypium hirsutum L.) field plots in arid climate at district Layyah, Punjab, Pakistan

Sucking pests are major threat to cotton field crop which cause unbearable losses to the crop yield. Aim of the current study was to record seasonal dynamics of major sucking insect pests including whitefly, jassid, thrips and their natural arthropod predators i.e. green lacewings and spiders in cotton field plots. The effects of surrounding field crops on pests’ density and predatory efficiency of predators were also recorded. For sampling and survey of insects, the visual counting was found to be the most efficient method for recording the abundance of insects, trailed by net sweeping and tapping. Whitefly was the most dominant sucking pest found on the vegetative stage of cotton, followed by jassid and thrips. Fluctuated populations of predatory arthropods, spiders and green lacewings were also recorded during whole cropping season however, the densities of pests and predators varied with crop phenology. Spiders’ population was encouraging at both vegetative and flowering stage and also the same trend of jassid and whitefly were observed at both stages of the crop. Surrounding habitats showed non-significant effect on population densities of insect pests and predators. For abiotic factors, the spiders showed strong positive correlation with humidity and temperature. However, green lacewing was only positively correlated with humidity. On the other hand, the populations of whitefly, jassid and thrips showed non-significant correlation with both temperature and humidity. Overall densities of sucking insect pests were found above economic threshold level. The plant age, crop stage and surrounding habitats effect on the population fluctuation of pests as well as the predators’ abundance. The future studies are also warranted to investigate the altered habitats and multiple trap cropping to find out their impact on unattended insect predators and parasitoids in cotton crop.

Estimation of Cotton Leaf Area Index (LAI) Based on Spectral Transformation and Vegetation Index

Unmanned aerial vehicles (UAV) has been increasingly applied to crop growth monitoring due to their advantages, such as their rapid and repetitive capture ability, high resolution, and low cost. LAI is an important parameter for evaluating crop canopy structure and growth without damage. Accurate monitoring of cotton LAI has guiding significance for nutritional diagnosis and the accurate fertilization of cotton. This study aimed to obtain hyperspectral images of the cotton canopy using a UAV carrying a hyperspectral sensor and to extract effective information to achieve cotton LAI monitoring. In this study, cotton field experiments with different nitrogen application levels and canopy spectral images of cotton at different growth stages were obtained using a UAV carrying hyperspectral sensors. Hyperspectral reflectance can directly reflect the characteristics of vegetation, and vegetation indices (VIs) can quantitatively describe the growth status of plants through the difference between vegetation in different band ranges and soil backgrounds. In this study, canopy spectral reflectance was extracted in order to reduce noise interference, separate overlapping samples, and highlight spectral features to perform spectral transformation; characteristic band screening was carried out; and VIs were constructed using a correlation coefficient matrix. Combined with canopy spectral reflectance and VIs, multiple stepwise regression (MSR) and extreme learning machine (ELM) were used to construct an LAI monitoring model of cotton during the whole growth period. The results show that, after spectral noise reduction, the bands screened by the successive projections algorithm (SPA) are too concentrated, while the sensitive bands screened by the shuffled frog leaping algorithm (SFLA) are evenly distributed. Secondly, the calculation of VIs after spectral noise reduction can improve the correlation between vegetation indices and LAI. The DVI (540,525) correlation was the largest after standard normal variable transformation (SNV) pretreatment, with a correlation coefficient of −0.7591. Thirdly, cotton LAI monitoring can be realized only based on spectral reflectance or VIs, and the ELM model constructed by calculating vegetation indices after SNV transformation had the best effect, with verification set R2 = 0.7408, RMSE = 1.5231, and rRMSE = 24.33%, Lastly, the ELM model based on SNV-SFLA-SNV-VIs had the best performance, with validation set R2 = 0.9066, RMSE = 0.9590, and rRMSE = 15.72%. The study results show that the UAV equipped with a hyperspectral sensor has broad prospects in the detection of crop growth index, and it can provide a theoretical basis for precise cotton field management and variable fertilization.

VERTICAL SPINDLE COTTON HARVESTER WITH SYMMETRIC MOVEMENT OF SPINDLE DRUMS

The article deals with the trends in the development of structures, research work on modernization and creation of new vertical spindle cotton harvesting apparatus (CHA). Authors developed new CHA that works as follows: the CHA with a cotton picker moves on the cotton field; the cotton plants getting into the inter-drum slots are processed, that is, the raw cotton be harvested. The CHA are in their original position before picking raw cotton. When a thick cotton plant gets into the inter-drum slot of the front pair of drums, the spindle drums move apart and the inter-drum slot opens, while the connecting rods and the sliders move forward, providing the symmetrical opening of the slot relative to the longitudinal line of the cotton plant row. Further, this thick plant falls into the inter-drum slot of the second pair of drums, while the inter-drum slot of the second drums opens, while the connecting rods and the sliders move along the guides forward, providing the symmetrical opening of the slot relative to the longitudinal line of the cotton plant rows. With such a pairwise symmetric movement of the SD, depending on the thickness of the cotton plant, the force of spindle pressing on the cotton plant from both sides is identical and symmetrical, since the SD move symmetrically to the longitudinal line passing along the cotton plant row.

Study on plowing of cotton soil using two-tier plow

The purpose of the study is to substantiate the parameters of a two-tier plow for plowing soil from under cotton. The basic principles and methods of classical mechanics, mathematical analysis and statistics were used in this study. The effects of the cotton field relief on the tillage and traction resistance of a two-tier plow were studied theoretically and experimentally. Analytical expressions are obtained for determining the uniformity of the course, the load of the bodies and the center of resistance of the plow, depending on its main parameters and the roughness of the relief of the cotton field. It is established that serial two-tier plows, due to the discrepancy between their width of the gripper and the width of the row spacing, do not meet the requirements of agricultural technology: the plowing depth is not stable, the coefficient of variation of the plowing depth reaches 16% for a trailed plow, and for a mounted plow - 25.8%; the transverse direction of the plough the bottom of the furrow turns out to be stepped; the value of the traction resistance changes at each pass of the plow. To improve the quality of plowing fields from under cotton, a new plowing method has been developed, carried out by a two-tier plow, the width of which is a multiple of the width of the row spacing of cotton. The width of the plow bodies is equal to half the width of the row spacing.

Integrated Optimization of Structure and Control Parameters for the Height Control System of a Vertical Spindle Cotton Picker

Vertical picking method is a predominate method used to harvest cotton crop. However, a vertical picking method may cause spindle bending of the cotton picker if spindles collide with stones on the cotton field. Thus, how to realize a precise height control of the cotton picker is a crucial issue to be solved. The objective of this study is to design a height control system to avoid the collision. To design it, the mathematical models are established first. Then a multi-objective optimization model represented by structure parameters and control parameters is proposed to take the pressure of chamber without piston, response time and displacement error of the height control system as the optimization objectives. An integrated optimization approach that combines optimization via simulation, particle swarm optimization and simulated annealing is proposed to solve the model. Simulation and experimental test results show that the proposed integrated optimization approach can not only reduce the pressure of chamber without piston, but also decrease the response time and displacement error of the height control system.