Browsing by Author "Guo, Wenxuan (TTU)"
Now showing 1 - 8 of 8
- Results Per Page
- Sort Options
Item Application of geographic information system and automated guidance system in optimizing contour and terrace farming(2018) Guo, Wenxuan (TTU)Farming contour and terrace fields using automated guidance systems with global navigation satellite system (GNSS) receivers requires appropriate geographic features for effective guidance and soil and water conservation. The objective of this paper was to develop methodologies for improving and designing guidance features for operating guidance systems in contour and terrace fields. This study was conducted in the Texas High Plains where contour and terrace farming practices are prevalent in slope fields. Four case studies were used to demonstrate the application of a geographic information system (GIS) in optimizing guidance geographic features, including line smoothing, line extending and connecting, creating swath AB lines, and guide-to-line features. Line smoothing removes sharp angularities and curve oscillations on guidance line features, resulting in smooth and more effective guidance operations. The line extension and connection method creates a more convenient and simple guidance feature by combining multiple AB lines. Guide-to-line features derived from AB lines can eliminate confusions when using a guidance system with multiple AB lines in fields with complicated topographic attributes. A methodology was also developed to create guidance AB lines by processing the elevation data generated by a guidance system with a real-time kinematic (RTK) receiver. Guidance line features created in this study satisfy user requirements for effective guidance operations and soil and water conservation. Integrating the application of GIS spatial analysis capabilities and automated guidance systems can enhance farming operations by improving or creating guidance line features, as well as satisfying soil and water conservation needs. Parameter selection for enhancing or creating guidance line features needs to consider unique field conditions and user requirements for simple, convenient, and effective field operations.Item Continuous monitoring of cotton stem water potential using Sentinel-2 imagery(2020) Lin, Yukun (TTU); Zhu, Zhe (TTU); Guo, Wenxuan (TTU); Sun, Yazhou (TTU); Yang, Xiaoyuan; Kovalskyy, ValeriyMonitoring cotton status during the growing season is critical in increasing production efficiency. The water status in cotton is a key factor for yield and cotton quality. Stem water potential (SWP) is a precise indicator for assessing cotton water status. Satellite remote sensing is an effective approach for monitoring cotton growth at a large scale. The aim of this study is to estimate cotton water stress at a high temporal frequency and at a large scale. In this study, we measured midday SWP samples according to the acquisition dates of Sentinel-2 images and used them to build linear-regression-based and machine-learning-based models to estimate cotton water stress during the growing season (June to August, 2018). For the linear-regression-based method, we estimated SWP based on different Sentinel-2 spectral bands and vegetation indices, where the normalized difference index 45 (NDI45) achieved the best performance (R2 = 0.6269; RMSE = 3.6802 (-1*swp (bars))). For the machine-learning-based method, we used random forest regression to estimate SWP and received even better results (R2 = 0.6709; RMSE = 3.3742 (-1*swp (bars))). To find the best selection of input variables for the machine-learning-based approach, we tried three different data input datasets, including (1) 9 original spectral bands (e.g., blue, green, red, red edge, near infrared (NIR), and shortwave infrared (SWIR)), (2) 21 vegetation indices, and (3) a combination of original Sentinel-2 spectral bands and vegetation indices. The highest accuracy was achieved when only the original spectral bands were used. We also found the SWIR and red edge band were the most important spectral bands, and the vegetation indices based on red edge and NIR bands were particularly helpful. Finally, we applied the best approach for the linear-regression-based and the machine-learning-based methods to generate cotton water potential maps at a large scale and high temporal frequency. Results suggests that the methods developed here has the potential for continuous monitoring of SWP at large scales and the machine-learning-based method is preferred.Item Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models(2021) Lin, Zhe (TTU); Guo, Wenxuan (TTU)An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R2), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.Item Detection of stress in cotton (Gossypium hirsutum L.) caused by aphids using leaf level hyperspectral measurements(2018) Chen, Tingting; Zeng, Ruier; Guo, Wenxuan (TTU); Hou, Xueying; Lan, Yubin; Zhang, LeiRemote sensing can be a rapid, accurate, and simple method for assessing pest damage on plants. The objectives of this study were to identify spectral wavelengths sensitive to cotton aphid infestation. Then, the normalized difference spectral indices (NDSI) and ratio spectral indices (RSI) based on the leaf spectrum were obtained within 350–2500 nm, and their correlation with infestation were qualified. The results showed that leaf spectral reflectance decreased in the visible range (350–700 nm) and the near-infrared range (NIR, 700–1300 nm) as aphid damage severity increased, and significant differences were found in blue, green, red, NIR and short-wave infrared (SWIR) band regions between different grades of aphid damage severity. Decrease in Chlorophyll a (Chl a) pigment was more significant than that in Chlorophyll (Chl b) in the infested plants and the Chl a/b ratio showed a decreasing trend with increase in aphid damage severity. The sensitive spectral bands were mainly within NIR and SWIR ranges. The best spectral indices NDSI (R678, R1471) and RSI (R1975, R1904) were formulated with these sensitive spectral regions through reducing precise sampling method. These new indices along with 16 other stress related indices compiled from literature were further tested for their ability to detect aphid damage severity. The two indices in this study showed significantly higher coefficients of determination (R2 of 0.81 and 0.81, p < 0.01) and the least RMSE values (RMSE of 0.50 and 0.49), and hence have potential application in assessing aphid infestation severity in cotton.Item Effects of irrigation rates on cotton yield as affected by soil physical properties and topography in the southern high plains(2021) Neupane, Jasmine (TTU); Guo, Wenxuan (TTU); West, Charles P. (TTU); Zhang, Fangyuan (TTU); Lin, Zhe (TTU)Lack of precipitation and groundwater for irrigation limits crop production in semi-arid regions, such as the Southern High Plains (SHP). Advanced technologies, such as variable rate irrigation (VRI), can conserve water and improve water use efficiency for sustainable agriculture. However, the adoption of VRI is hindered by the lack of on-farm research focusing on the feasibility of VRI. The objective of this study was to assess the effect of irrigation rates on cotton yield as affected by soil physical properties and topography in the Southern High Plains. This study was conducted in two fields within a 194-ha commercially managed farm in Hale County, Texas, in 2017. An irrigation treatment with three rates was implemented in a randomized complete block design with two replications as separate blocks in each field. A total of 230 composite soil samples were collected from the farm in spring 2017 and analyzed for texture. Information on apparent soil electrical conductivity (ECa), elevation, and final yield were collected from the fields. A statistical model showed that the effect of irrigation rates on cotton yield depended on its interaction with soil physical properties and topography. For example, areas with slope >2% and sand content >50% had no significant response to higher irrigation rates. This model suggests that applying irrigation amounts based on the yield response can be a basis for VRI. This study provides valuable information for site-specific irrigation to optimize crop production in fields with significant variability in soil physical properties and topography.Item Reflectance-based Model for Soybean Mapping in United States at Common Land Unit Scale with Landsat 8(2019) Gusso, Aníbal; Guo, Wenxuan (TTU); Rolim, Silvia Beatriz AlvesThe objective of this study is to validate the feasibility of a reflectance-based model for soybean crop area classification in advance of the county scale statistics from the United States Department of Agriculture (USDA). This classification method is named Reflectance-based North American Model (RNAM). It operates through the analysis of the main physically driven characteristics of farm fields and their specific radiometric profile obtained from Operational Land Imager (OLI) onboard Landsat 8. The state area of Illinois/US was selected because it is the largest soybean producer and accounted for nearly 35 percent of the total soybeans production in US. Farm fields within a set of 32 counties were analyzed for six crop years between 2013 to 2018. Results obtained from RNAM were compared to official estimates of USDA at county level. Coefficients R2 ranged between 0.92 and 0.96, indicating good agreement of the estimates. Results from RNAM were also validated with the geospatial reference map Cropland Data Layer (CDL) of soybeans from USDA. The overall map accuracy found was 93.86% with Kappa Index of Agreement of 0.795. Thus, RNAM was considered able to provide timely thematic soybean maps, in late September, in advance of the county scale statistics from USDA.Item Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning(2020) Lin, Zhe (TTU); Guo, Wenxuan (TTU)Machine learning and computer vision technologies based on high-resolution imagery acquired using unmanned aerial systems (UAS) provide a potential for accurate and efficient high-throughput plant phenotyping. In this study, we developed a sorghum panicle detection and counting pipeline using UAS images based on an integration of image segmentation and a convolutional neural networks (CNN) model. A UAS with an RGB camera was used to acquire images (2.7 mm resolution) at 10-m height in a research field with 120 small plots. A set of 1,000 images were randomly selected, and a mask was developed for each by manually delineating sorghum panicles. These images and their corresponding masks were randomly divided into 10 training datasets, each with a different number of images and masks, ranging from 100 to 1,000 with an interval of 100. A U-Net CNN model was built using these training datasets. The sorghum panicles were detected and counted by a predicted mask through the algorithm. The algorithm was implemented using Python with the Tensorflow library for the deep learning procedure and the OpenCV library for the process of sorghum panicle counting. Results showed the accuracy had a general increasing trend with the number of training images. The algorithm performed the best with 1,000 training images, with an accuracy of 95.5% and a root mean square error (RMSE) of 2.5. The results indicate that the integration of image segmentation and the U-Net CNN model is an accurate and robust method for sorghum panicle counting and offers an opportunity for enhanced sorghum breeding efficiency and accurate yield estimation.Item Spatial and temporal trends of irrigated cotton yield in the southern high plains(2018) Guo, Wenxuan (TTU)Understanding spatial and temporal variability patterns of crop yield and their relationship with soil properties can provide decision support to optimize crop management. The objectives of this study were to (1) determine the spatial and temporal variability of cotton (Gossypium hirsutum L.) lint yield over different growing seasons; (2) evaluate the relationship between spatial and temporal yield patterns and apparent soil electrical conductivity (ECa). This study was conducted in eight production fields, six with 50 ha and two with 25 ha, on the Southern High Plains (SHP) from 2000 to 2003. Cotton yield and ECa data were collected using a yield monitor and an ECa mapping system, respectively. The amount and pattern of spatial and temporal yield variability varied with the field. Fields with high variability in ECa exhibited a stronger association between spatial and temporal yield patterns and ECa, indicating that soil properties related to ECa were major factors influencing yield variability. The application of ECa for site-specific management is limited to fields with high spatial variability and with a strong association between yield spatial and temporal patterns and ECa variation patterns. For fields with low variability in yield, spatial and temporal yield patterns might be more influenced by weather or other factors in different growing seasons. Fields with high spatial variability and a clear temporal stability pattern have great potential for long-term site-specific management of crop inputs. For unstable yield, however, long-term management practices are difficult to implement. For these fields with unstable yield patterns, within season site-specific management can be a better choice. Variable rate application of water, plant growth regulators, nitrogen, harvest aids may be implemented based on the spatial variability of crop growth conditions at specific times.