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.

Factors Affecting Adult Captures of the Cotton Bollworm, Helicoverpa armigera (Hübner) (Lepidoptera: Noctuidae) in Pheromone-Baited Traps

The effects of funnel-trap color, trap height and pheromone formulation on the adult captures of the cotton bollworm, Helicoverpa armigera (Hübner) (Lepidoptera: Noctuidae) were evaluated in traps that were suspended in cotton fields in central Greece. Briefly, in a first trial, the efficacy of funnel traps of three different colors, i.e., green, striped (with black and white stripes) and white, was comparatively evaluated, whereas in a second trial green funnel traps were placed at three heights, i.e., 30, 60 and 90 cm from the ground. Finally, in a third trial we tested the efficiency of green funnel traps with three commercially available pheromone lures. Considering the overall captures, trap color and pheromone formulation affected male captures, whereas trap height had no influence. Captures notably increased in all traps from late August to mid-September. In total, the white funnel trap captured more moths than the green or striped funnel traps. Placement of the traps at different heights did not significantly affect captures, but seasonal differences were observed at individual dates during the trapping period. Barrettine’s pheromone lure provided significantly more captures than the other two (Russell, Trécé) in some of the trap-check dates. The results can be further utilized in the monitoring protocols of H. armigera in cotton fields.

Integrating Sentinel-1/2 Data and Machine Learning to Map Cotton Fields in Northern Xinjiang, China

Timely and accurate information of cotton planting areas is essential for monitoring and managing cotton fields. However, there is no large-scale and high-resolution method suitable for mapping cotton fields, and the problems associated with low resolution and poor timeliness need to be solved. Here, we proposed a new framework for mapping cotton fields based on Sentinel-1/2 data for different phenological periods, random forest classifiers, and the multi-scale image segmentation method. A cotton field map for 2019 at a spatial resolution of 10 m was generated for northern Xinjiang, a dominant cotton planting region in China. The overall accuracy and kappa coefficient of the map were 0.932 and 0.813, respectively. The results showed that the boll opening stage was the best phenological phase for mapping cotton fields and the cotton fields was identified most accurately at the early boll opening stage, about 40 days before harvest. Additionally, Sentinel-1 and the red edge bands in Sentinel-2 are important for cotton field mapping, and there is great potential for the fusion of optical images and microwave images in crop mapping. This study provides an effective approach for high-resolution and high-accuracy cotton field mapping, which is vital for sustainable monitoring and management of cotton planting.

Comparison of Efficiency-Enhanced Management and Conventional Management of Irrigation and Nitrogen Fertilization in Cotton Fields of Northwestern China

Excessive application of nitrogen fertilizers and improper methods of irrigation under conventional management are common problems in the cotton fields of northwestern China. Efficiency-enhanced management, based on the water and nitrogen dynamics and crop requirements, has been used as a valuable strategy in different crops. The present study aimed to compare efficiency-enhanced management and conventional management of irrigation and nitrogen fertilization in the cotton fields at the Junggar Basin (Shihezi) and Tarim Basin (Cele) of northwestern China. Compared with conventional management, efficiency-enhanced management reduced the amount of N fertilizer by 41% in Cele and 44% in Shihezi, and the irrigation quantity by 35% in Cele and 24% in Shihezi. However, the cotton yield under efficiency-enhanced management was similar to that found under conventional management at both the experimental sites. The efficiency-enhanced management increased the water-use efficiency (WUE) and reduced the residual soil mineralizable N (Nmin) and apparent N losses. This study indicated that efficiency-enhanced management can significantly enhance the utilization efficiency of irrigation water and N fertilizers for cotton production in the fields of northwestern China.

Soil salinity variations and cotton growth under long-term mulched drip irrigation in saline-alkali land of arid oasis

The sustainable development and utilization of saline-alkali land are closely related to holding fast the minimum cultivated land area of China. The change of soil salt in cotton field under long-term mulched drip irrigation (MDI) is connected with the development of the national cotton industry. From 2015 to 2019, five cotton fields with different applying years of MDI, which were reclaimed in 2004, 2008, 2010, 2012 and 2015 respectively and were saline-alkali wasteland before, were monitored continuously in the Manas River irrigation area of Xinjiang. By means of continuous location monitoring and spatial–temporal variability (For example, the monitoring data of cotton fields under MDI in 2004, 2008, 2010, 2012 and 2015, and in the year of 2015 were counted as 12, 8, 6, 4 and 1 years, respectively), the spatial–temporal variations of soil salt and ions in cotton field with 1-16a MDI technology were presented. The cotton growth characteristics and its main influencing factors were also analyzed in the study. The results showed that saline-alkali cotton field experienced changed from intensive saline soil to moderate saline soil and finally to non-saline soil under long-term MDI. The change of soil salt and the response of cotton growth to soil salt were divided into three typical stages. Firstly, soil desalinated rapidly in 1-4a MDI cotton field, which the annual average desalination rate was 24.93% in 0–100 cm soil layer (root zone). Additionally, the survival rate of cotton rocketed from 1.48% to 42.04%, and yield increased sharply from 72.43 kg ha−1 to 3075.90 kg ha−1. Soil desalination was lower in 5-11a MDI cotton field, which the annual average desalination rate was 10.92% at the root zone. The annual survival rate and yield of cotton increased by 6.26% and 5.18%, respectively. After 12a MDI, the soil salt in cotton field tended to be generally constant, which the average salt content in root zone was less than 2.49 g kg−1. The survival rate of cotton was stable above 90.39%, and the yield per unit area exceeded 5401.32 kg ha−1. Ions, sodium absorption ratio and Cl− and SO42− equivalent ratio (CSER) in cotton soil also decreased with the extension of MDI. Salt composition changed year by year, but the type of intensive saline soil had always been chloride-sulphate solonchak (0.2 < CSER < 1). In practice, with a higher irrigation quota and ideal irrigation water quality, the soil salt environment of saline-alkali soil MDI cotton field had developed in favor of cotton growth in an oasis irrigation area. However, this management practice caused between 124.21–143.61 mm of water resources waste. Therefore, we should further enhanced the consciousness of water-saving and implemented quota management in practice.

Species determination and CYTB-G143A monitoring of Ramulariopsis spp. isolated from cotton in Brazil

Ramularia leaf spot is a disease of major importance on cotton fields in Brazil due to its effects on yield and cotton fiber quality. Two Ramulariopsis (syn. Ramularia) species, R. gossypii and R. pseudoglycines, are reported as the causal agents of this disease, but it is unknown which species is the most prevalent in Brazilian cotton fields. The goal of this work was to determine the most frequent species occurring on field samples from a molecular monitoring program which sampled from all cotton growing regions in Brazil from 2017 to 2020 seasons. We also used molecular tools for genotyping a region of the Cytb gene for all sampled isolates. Sequencing of an ITS-rDNA region was used for Ramulariopsis species determination, and a DNA fragment from the Cytb gene was amplified, sequenced, and analyzed for all 165 isolates. The ITS-rDNA sequencing confirmed that all isolates belong to the Ramulariopsis, and most notably, all the SNPs observed in this region, are of the R. pseudoglycines species for all 165 isolates, thus all analyzed isolates were assigned to this species. The analysis of the Cytb gene fragment sequenced showed the presence of the G143A substitution, and absence of G137R substitution, in all 165 isolates.

THE INFLOW OF RUSSIAN CAPITAL AND INDUSTRY INTO THE BUKHARA EMIRATE IN THE LATE 19TH AND EARLY 20TH CENTURIES

Beginning in the 80 years of 19th century , the Russian government and entrepreneurs began to invest in the development of protected and gray lands in the emirate, as well as in the expansion of cotton fields. It also introduced an industry related to the processing of raw cotton grown in the emirate. It also pursued a policy of relocating the military and Russian citizens to major cities in the emirate.