Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 222, С. 109022 - 109022

Опубликована: Май 12, 2024

Язык: Английский

---

Improving Wheat Leaf Nitrogen Concentration (LNC) Estimation across Multiple Growth Stages Using Feature Combination Indices (FCIs) from UAV Multispectral Imagery

Agronomy, Год журнала: 2024, Номер 14(5), С. 1052 - 1052

Опубликована: Май 15, 2024

Leaf nitrogen concentration (LNC) is a primary indicator of crop status, closely related to the growth and development dynamics crops. Accurate efficient monitoring LNC significant for precision field management enhancing productivity. However, biochemical properties canopy structure wheat change across different stages, leading variations in spectral responses that significantly impact estimation LNC. This study aims investigate construction feature combination indices (FCIs) sensitive multiple using remote sensing data develop an model suitable stages. The research employs UAV multispectral technology acquire imagery during early (Jointing stage Booting stage) late (Early filling Late stages) 2021 2022, extracting band reflectance texture metrics. Initially, twelve (SFCIs) were constructed information. Subsequently, (TFCIs) created metrics as alternative bands. Machine learning algorithms, including partial least squares regression (PLSR), random forest (RFR), support vector (SVR), Gaussian process (GPR), used integrate information, performance Results show Red, Red edge, Near-infrared bands, along with such Mean, Correlation, Contrast, Dissimilarity, has potential estimation. SFCIs TFCIs both enhanced responsiveness Additionally, index, Modified Vegetation Index (MVI), demonstrated improvement over NDVI, correcting over-saturation concerns NDVI time-series analysis displaying outstanding Spectral information outperforms capability, their integration, particularly SVR, achieves highest (coefficient determination (R2) = 0.786, root mean square error (RMSE) 0.589%, relative prediction deviation (RPD) 2.162). In conclusion, FCIs developed this improve enabling precise provides insights technical nutrition status

Язык: Английский

---

Automated Phenotypic Analysis of Mature Soybean Using Multi-View Stereo 3D Reconstruction and Point Cloud Segmentation

Agriculture, Год журнала: 2025, Номер 15(2), С. 175 - 175

Опубликована: Янв. 14, 2025

Phenotypic analysis of mature soybeans is a critical aspect soybean breeding. However, manually obtaining phenotypic parameters not only time-consuming and labor intensive but also lacks objectivity. Therefore, there an urgent need for rapid, accurate, efficient method to collect the soybeans. This study develops novel pipeline acquiring traits based on three-dimensional (3D) point clouds. First, clouds are obtained using multi-view stereo 3D reconstruction method, followed by preprocessing construct dataset. Second, deep learning-based network, PVSegNet (Point Voxel Segmentation Network), proposed specifically segmenting pods stems. network enhances feature extraction capabilities through integration cloud voxel convolution, as well orientation-encoding (OE) module. Finally, such stem diameter, pod length, width extracted validated against manual measurements. Experimental results demonstrate that average Intersection over Union (IoU) semantic segmentation 92.10%, with precision 96.38%, recall 95.41%, F1-score 95.87%. For instance segmentation, achieves (AP@50) 83.47% (AR@50) 87.07%. These indicate feasibility In plant parameters, predicted values width, diameter exhibit coefficients determination (R2) 0.9489, 0.9182, 0.9209, respectively, demonstrates our can significantly improve efficiency accuracy, contributing application automated technology in

Язык: Английский

---

Enhancing the accuracy of monitoring effective tiller counts of wheat using multi-source data and machine learning derived from consumer drones

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 232, С. 110120 - 110120

Опубликована: Фев. 24, 2025

Язык: Английский

---

Combining vegetation, color, and texture indices with hyperspectral parameters using machine-learning methods to estimate nitrogen concentration in rice stems and leaves

Field Crops Research, Год журнала: 2023, Номер 304, С. 109175 - 109175

Опубликована: Ноя. 1, 2023

Язык: Английский

---

Combining features selection strategy and features fusion strategy for SPAD estimation of winter wheat based on UAV multispectral imagery

Frontiers in Plant Science, Год журнала: 2024, Номер 15

Опубликована: Май 10, 2024

The Soil Plant Analysis Development (SPAD) is a vital index for evaluating crop nutritional status and serves as an essential parameter characterizing the reproductive growth of winter wheat. Non-destructive accurate monitorin3g wheat SPAD plays crucial role in guiding precise management nutrition. In recent years, spectral saturation problem occurring later stage has become major factor restricting accuracy estimation. Therefore, purpose this study to use features selection strategy optimize sensitive remote sensing information, combined with fusion integrate multiple characteristic features, order improve estimating SPAD. This conducted field experiments different varieties nitrogen treatments, utilized UAV multispectral sensors obtain canopy images during heading, flowering, late filling stages, extracted texture from images, employed (Boruta Recursive Feature Elimination) prioritize features. Support Vector Machine Regression algorithm are applied construct estimation model results showed that NIR band other bands can fully capture differences stage, red more During stability constructed using both superior models only single feature or no strategy. enhancement by method becomes significant, greatest improvement observed R 2 increasing 0.092-0.202, root mean squared error (RMSE) decreasing 0.076-4.916, ratio performance deviation (RPD) 0.237-0.960. conclusion, excellent application potential stages growth, providing theoretical basis technical support precision nutrient crops.

Язык: Английский

---

Application of unmanned aerial vehicle optical remote sensing in crop nitrogen diagnosis: A systematic literature review

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 227, С. 109565 - 109565

Опубликована: Окт. 24, 2024

Язык: Английский

---

Estimation of winter wheat LAI based on color indices and texture features of RGB images taken by UAV

Journal of the Science of Food and Agriculture, Год журнала: 2024, Номер 105(1), С. 189 - 200

Опубликована: Авг. 16, 2024

Abstract Background Leaf area index (LAI) is an important indicator for assessing plant growth and development, also closely related to photosynthesis in plants. The realization of rapid accurate estimation crop LAI plays role guiding farmland production. In study, the UAV‐RGB technology was used estimate based on 65 winter wheat varieties at different fertility periods, including farm varieties, main cultivars, new lines, core germplasm foreign varieties. Color indices (CIs) texture features were extracted from RGB images determine their quantitative link LAI. Results results revealed that among image features, exhibited a significant positive correlation with CIs ( r = 0.801), whereas there negative −0.783). Furthermore, visible atmospheric resistance index, green–red vegetation modified CIs, mean demonstrated strong > 0.8. With reference model input variables, backpropagation neural network (BPNN) R 2 0.730, RMSE 0.691, RPD 1.927) outperformed other models constructed by individual variables. Conclusion This study offers theoretical basis technical precise monitor consumer‐level UAVs. BPNN model, incorporating proved be superior estimating LAI, offered reliable method monitoring wheat. © 2024 Society Chemical Industry.

Язык: Английский

---

Unmanned aerial vehicles (UAVs)-based crop lodging susceptibility and seed yield assessment during different growth stages of rapeseed (Brassica napus)

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 221, С. 108980 - 108980

Опубликована: Апрель 30, 2024

Язык: Английский

---

Combining UAV Multispectral and Thermal Infrared Data for Maize Growth Parameter Estimation

Agriculture, Год журнала: 2024, Номер 14(11), С. 2004 - 2004

Опубликована: Ноя. 7, 2024

The leaf area index (LAI) and chlorophyll content (LCC) are key indicators of crop photosynthetic efficiency nitrogen status. This study explores the integration UAV-based multispectral (MS) thermal infrared (TIR) data to improve estimation maize LAI LCC across different growth stages, aiming enhance (N) management. In field trials from 2022 2023, UAVs captured canopy images under varied water treatments, while were measured. Estimation models, including partial least squares regression (PLS), convolutional neural networks (CNNs), random forest (RF), developed using spectral, thermal, textural data. results showed that MS (spectral features) had strong correlations with LCC, CNN models yielded accurate estimates (LAI: R2 = 0.61–0.79, RMSE 0.02–0.38; LCC: 0.63–0.78, 2.24–0.39 μg/cm2). Thermal reflected but limitations in estimating LCC. Combining TIR significantly improved accuracy, increasing values for by up 23.06% 19.01%, respectively. Nitrogen dilution curves estimated LAIs effectively diagnosed N Deficit irrigation reduced uptake, intensifying deficiency, proper management enhanced

Язык: Английский

---