Unmanned aerial vehicle (UAV) platforms with sensors covering the red-edge and near-infrared (NIR) bands to measure vegetation indices (VIs) have been recently introduced in agriculture research. Consequently, VIs originally developed for traditional airborne spaceborne become applicable UAV systems. In this study, we investigated difference tillage treatments cotton sorghum using various RGB NIR VIs. Minimized has known increase farm sustainability potentially optimize productivity over...

This study presents a comparative of multispectral and RGB (red, green, blue) sensor-based cotton canopy cover modelling using multi-temporal unmanned aircraft systems (UAS) imagery. Additionally, model an sensor is proposed that combines RGB-based vegetation index with morphological closing. The field experiment was established in 2017 2018, where the whole area divided into approximately 1 x m size grids. Grid-wise percentage computed both sensors over multiple flights during growing...

Assessing plant population of cotton is important to make replanting decisions in low density areas, prone yielding penalties. Since the measurement field labor intensive and subject error, this study, a new approach image-based counting proposed, using unmanned aircraft systems (UAS; DJI Mavic 2 Pro, Shenzhen, China) data. The previously developed techniques required priori information geometry or statistical characteristics canopy features, while also limiting versatility methods variable...

Accurately deriving remote sensing reflectance (Rrs) from satellite imagery in optically complex inland and coastal waters is critical for water quality monitoring management. This study presents AQUAVERSE (an aquatic inversion scheme of fresh waters), an innovative machine learning-based atmospheric correction (AC) framework, that leverages Mixture Density Networks (MDNs) to retrieve high-quality Rrs multispectral data acquired by Landsat-8/9 (OLI) Sentinel-2A/B (MSI) satellites. By...

Constructing a robust ocean color (OC) record (e.g., water transparency, phytoplankton absorption) for long-term assessments of coastal and inland ecosystems from past, present, future missions requires high-quality spectral remote sensing reflectance ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${R} _{\text {rs}}$ </tex-math></inline-formula> ) products. Using the GLORIA dataset (Lehmann et al.,...

Recent years have witnessed enormous growth in Unmanned Aircraft System (UAS) and sensor technology which made it possible to collect high spatial temporal resolutions data over the crops throughout growing season. The objective of this research is develop a novel machine learning framework for marketable tomato yield estimation using multi-source spatio-temporal remote sensing collected from UAS. proposed model based on Artificial Neural Network (ANN) takes UAS multi-temporal features such...

Tar spot is a foliar disease of corn characterized by fungal fruiting bodies that resemble tar spots. The emerged in the U.S. 2015, and severe outbreaks 2018 caused an economic impact on yields throughout Midwest. Adequate epidemiological surveillance quantification are necessary to develop immediate long-term management strategies. This study presents measurement framework evaluates severity using unmanned aircraft systems (UAS)-based plant phenotyping regression techniques. UAS-based...

Tomato production faces constant pressure of biotic and abiotic stresses that can cause significant loss fruit quality. In tropical subtropical climates, the main disease affecting tomato is caused by Yellow Leaf Curl Virus (TYLCV), a virus vectored silverleaf whitefly (Bemisia tabaci). The method control relies on insecticide spray to vector, avoiding spread disease. Detecting spatially locating infected plants are required prevent epidemic outbreak TYLCV. this study, we aim develop an...

A partitional clustering-based segmentation is used to carry out supervised classification for hyperspectral images. The main contribution of this study lies in the use projected and correlation clustering techniques perform image segmentation. These types have capability concurrently feature/band reduction, are also able identify different sets relevant features clusters. Using these map obtained, which combined with pixel-level support vector machines (SVM) result, using majority voting....

Unmanned Aerial System (UAS) is becoming a popular choice when acquiring fine spatial resolution images for precision agriculture applications. Compared to other remote sensing data collection platforms, UAS can acquire image at relatively lower cost with finer more flexible schedule. In recent years, multispectral sensors that capture near infrared (NIR) and red edge spectral reflectance have been successfully integrated UAS, it offering versatility in soil field analysis, crop monitoring,...

Immense growth is witnessed in the application of unmanned aircraft systems (UAS) for precision agriculture recent years. Though UAS can provide precise high spatial resolution data, large aerial coverage still practically not feasible due to limited battery, flight time and size data. Contrarily, satellite images cover larger area but coarser data compared imagery. The objective this research was combine UAS's ability with vast areal provided by estimate canopy parameters. Experimental...

In this study, an ensemble classifier based method is investigated to detect and discard mislabelled training samples from set. To decide, whether a sample the set, majority voting considered for constructed using kNN, RBF neural network SVM which are diverse in their decision making. Further, compared with conventional statistical anomaly detection filter multi-objective Genetic Algorithm (GA) filters, terms of its ability handle number mislabeled present The performance all filters tested...

Accurate segmentation of fluorescence images has become increasingly important for recognizing cell nucleus that have the phenotype interest in biomedical applications. In this study an ensemble based method is proposed cancer microscopy images. The const ructed and compared using Bayes graph-cut algorithm, binary spatial fuzzy C-means, level set which were chosen their accuracy efficiency area. We investigate performance each separately finally compare results with method. Experiments are...

The objective of this research is to develop a novel machine learning framework for automatic cotton genotype selection using multi-source and spatio-temporal remote sensing data collected from Unmanned Aerial System (UAS). proposed model based on Artificial Neural Network (ANN) it takes UAS multi-temporal features such as canopy cover, height, volume, Normalized Difference Vegetation Index (NDVI), Excessive Greenness along with non-temporal boll count, size volume input predicts the...

Tar spot is a foliar disease of corn characterized by raised black spots that may or not be surrounded tan brown halo called fisheye. Severe infection can lead to 10-50% yield loss in corn. Timely detection early symptoms essential for implementing management tactics reduce the disease. This study aims propose machine learning pipeline estimate severity tar using unmanned aircraft systems (UAS) data. The overall process comprises structure from motion (SfM), canopy attributes extraction,...

Abstract The use of unmanned aerial vehicles (UAVs) to identify the number and area cotton ( Gossypium hirsutum L.) bolls in a field plot can serve as an important high‐throughput phenotyping strategy for predicting seedcotton yield. objectives this study were determine if prediction yield using UAV could be improved skip‐row spacing versus solid‐row genotype × row‐spacing interaction occurs fiber traits. A split‐plot design was used with main being row sub‐plot consisting five genotypes....