Comparison of CWSI and Ts-Ta-VIs in moisture monitoring of dryland crops (sorghum and maize) based on UAV remote sensing

Journal of Integrative Agriculture, Год журнала: 2024, Номер 23(7), С. 2458 - 2475

Опубликована: Март 11, 2024

Monitoring agricultural drought using remote sensing data is crucial for precision irrigation in modern agriculture. Utilizing unmanned aerial vehicle (UAV) sensing, this study explored the applicability of an empirical crop water stress index (CWSI) based on canopy temperature and three-dimensional indices (TDDI) constructed from surface (Ts), air (Ta) five vegetation (VIs) monitoring moisture status dryland crops. Three machine learning algorithms (random forest regression [RFR], support vector regression, partial least squares regression) were used to compare performance content (VMC) estimation sorghum maize. The main results as follows: (1) Comparative analysis revealed that Ts-Ta-Normalized Difference Vegetation Index (TDDIn) Ts-Ta-Enhanced (TDDIe) more strongly correlated with VMC compared other indices. exhibited varying sensitivities under different regimes; strongest correlation observed was TDDIe maize fully irrigated treatment (r=−0.93); (2) Regarding spatial temporal characteristics, TDDIn, CWSI showed minimal differences over experimental period, coefficients variation 0.25, 0.18 0.24, respectively. All three capable effectively characterizing distribution crops, but TDDI accurately monitored after a rainfall or event. (3) For prediction single RFR models TDDIn estimated most (R20.7), TDDIn-based model predicted highest accuracy when considering multiple-crop samples, R2 RMSE 0.62 14.26%, Thus, proved effective than estimating content.

Язык: Английский

---

A critical review on multi-sensor and multi-platform remote sensing data fusion approaches: current status and prospects

International Journal of Remote Sensing, Год журнала: 2024, Номер unknown, С. 1 - 76

Опубликована: Дек. 11, 2024

Numerous remote sensing (RS) systems currently collect data about Earth and its environments. However, each system provides limited in terms of spatial resolution, spectral information, other parameters. Given technological constraints, combining from diverse sources can effectively enhance RS solutions through enrichment. Many studies have investigated the fusion acquired different sensors platforms. This paper a comprehensive review research on multi-platform -sensor fusion, encompassing visible-light images, multi/hyper-spectral RADAR LiDAR point clouds, thermal spectrometry samples, geophysical data. An analysis over 950 papers revealed that feature-level multi-sensor was most commonly employed technique, surpassing pixel- decision-level approaches. Moreover, satellite more prevalent than manned unmanned aerial vehicles. The integration initially gained traction applications such as precision agriculture before expanding to land use cover mapping. addresses previously overlooked issues presents framework facilitate seamless Guidelines for this include ensuring same acquisition time, co-registration, true orthorectification, consistent resolution or information content, radiometric consistency, wavelength band coverage.

Язык: Английский

---

Monitoring of Antarctica’s Fragile Vegetation Using Drone-Based Remote Sensing, Multispectral Imagery and AI

Sensors, Год журнала: 2024, Номер 24(4), С. 1063 - 1063

Опубликована: Фев. 6, 2024

Vegetation in East Antarctica, such as moss and lichen, vulnerable to the effects of climate change ozone depletion, requires robust non-invasive methods monitor its health condition. Despite increasing use unmanned aerial vehicles (UAVs) acquire high-resolution data for vegetation analysis Antarctic regions through artificial intelligence (AI) techniques, multispectral imagery deep learning (DL) is quite limited. This study addresses this gap with two pivotal contributions: (1) it underscores potential a field notably limited implementations these datasets; (2) introduces an innovative workflow that compares performance between supervised machine (ML) classifiers: Extreme Gradient Boosting (XGBoost) U-Net. The proposed validated by detecting mapping lichen using collected highly biodiverse Specially Protected Area (ASPA) 135, situated near Casey Station, January February 2023. implemented ML models were trained against five classes: Healthy Moss, Stressed Moribund Lichen, Non-vegetated. In development U-Net model, applied: Method which utilised original labelled those used XGBoost; incorporated XGBoost predictions additional input version Results indicate demonstrated performance, exceeding 85% key metrics precision, recall, F1-score. suggested enhanced accuracy classification outputs U-Net, 2 substantial increase recall F1-score compared 1, notable improvements precision Moss (Method 2: 94% vs. 1: 74%) 86% 69%). These findings contribute advancing monitoring techniques delicate ecosystems, showcasing UAVs, imagery, remote sensing applications.

Язык: Английский

---

Compression Approaches for LiDAR Point Clouds and Beyond: A Survey

ACM Transactions on Multimedia Computing Communications and Applications, Год журнала: 2025, Номер unknown

Опубликована: Янв. 31, 2025

With the widespread use of LiDAR sensors in autonomous driving, point cloud compression (LPCC) plays an important role effectively managing storage, transmission, and perception growing volume data. Despite this need, there has been a noticeable absence comprehensive investigations specifically dedicated to LPCC methods. To address issue, paper presents systematic survey existing LPCCs, aiming summarize recent progress inspire future research field. We begin by providing general introduction fundamentals, covering latest (LPC) datasets, distinctive attributes, evaluation metrics, data formats. then conduct careful review comparison examining image-based, octree-based, deep-learned, other approaches, offering valuable insights into strengths weaknesses cutting-edge models. Finally, we propose directions based on limitations LPCCs. believe that findings presented will contribute deeper understanding LPCCs promote further development sensor-based systems.

Язык: Английский

---

Improving winter wheat plant nitrogen concentration prediction by combining proximal hyperspectral sensing and weather information with machine learning

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 232, С. 110072 - 110072

Опубликована: Фев. 6, 2025

Язык: Английский

---

Mapping Harmful Algae Blooms: The Potential of Hyperspectral Imaging Technologies

Remote Sensing, Год журнала: 2025, Номер 17(4), С. 608 - 608

Опубликована: Фев. 11, 2025

Harmful algae blooms (HABs) pose critical threats to aquatic ecosystems and human economies, driven by their rapid proliferation, oxygen depletion capacity, toxin release, biodiversity impacts. These blooms, increasingly exacerbated climate change, compromise water quality in both marine freshwater ecosystems, significantly affecting life coastal economies based on fishing tourism while also posing serious risks inland bodies. This article examines the role of hyperspectral imaging (HSI) monitoring HABs. HSI, with its superior spectral resolution, enables precise classification mapping diverse species, emerging as a pivotal tool environmental surveillance. An array HSI techniques, algorithms, deployment platforms are evaluated, analyzing efficacy across varied geographical contexts. Notably, sensor-based studies achieved up 90% accuracy, regression-based chlorophyll-a (Chl-a) estimations frequently reaching coefficients determination (R2) above 0.80. quantitative findings underscore potential for robust HAB diagnostics early warning systems. Furthermore, we explore current limitations future management, highlighting strategic importance addressing growing economic challenges posed paper seeks provide comprehensive insight into HSI’s capabilities, fostering integration global strategies against proliferation.

Язык: Английский

---

Spatial predictions of soil moisture across a longitudinal gradient in semiarid ecosystems using UAV and RGB sensors

Geocarto International, Год журнала: 2025, Номер 40(1)

Опубликована: Март 2, 2025

Язык: Английский

---

What Is the Predictive Capacity of Sesamum indicum L. Bioparameters Using Machine Learning with Red–Green–Blue (RGB) Images?

AgriEngineering, Год журнала: 2025, Номер 7(3), С. 64 - 64

Опубликована: Март 3, 2025

The application of machine learning techniques to determine bioparameters, such as the leaf area index (LAI) and chlorophyll content, has shown significant potential, particularly with use unmanned aerial vehicles (UAVs). This study evaluated RGB images obtained from UAVs estimate bioparameters in sesame crops, utilizing data selection methods. experiment was conducted at Federal Rural University Pernambuco involved using a portable AccuPAR ceptometer measure LAI spectrophotometry photosynthetic pigments. Field were captured DJI Mavic 2 Enterprise Dual remotely piloted aircraft equipped thermal cameras. To manage high dimensionality data, CRITIC Pearson correlation methods applied select most relevant indices for XGBoost model. divided into training, testing, validation sets ensure model generalization, performance assessed R2, MAE, RMSE metrics. effectively estimated LAI, a, total chlorophyll, carotenoids (R2 > 0.7) but had limited b. found be effective method algorithm.

Язык: Английский

---

Knowledge graph exploitation to enhance the usability of risk assessment in construction safety planning

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103305 - 103305

Опубликована: Апрель 23, 2025

Язык: Английский

---

Integration of Hybrid Networks, AI, Ultra Massive-MIMO, THz Frequency, and FBMC Modulation Toward 6G Requirements: A Review

IEEE Access, Год журнала: 2023, Номер 12, С. 483 - 513

Опубликована: Дек. 21, 2023

The fifth-generation (5G) wireless communications have been deployed in many countries with the following features: networks at 20 Gbps as peak data rate, a latency of 1 ms, reliability 99.999%, maximum mobility 500 km/h, bandwidth GHz, and capacity 10 ⁶ up to Mbps/m xmlns:xlink="http://www.w3.org/1999/xlink">2 . Nonetheless, rapid growth applications, such extended/virtual reality (XR/VR), online gaming, telemedicine, cloud computing, smart cities, Internet Everything (IoE), others, demand lower latency, higher rates, ubiquitous coverage, better reliability. These requirements are main problems that challenged 5G while concurrently encouraging researchers practitioners introduce viable solutions. In this review paper, sixth-generation (6G) technology could solve limitations, achieve requirements, support future applications. integration multiple access techniques, terahertz (THz), visible light (VLC), ultra-massive multiple-input multiple-output (um-MIMO), hybrid networks, cell-free massive MIMO, artificial intelligence (AI)/machine learning (ML) proposed for 6G. contributions paper comprehensive 6G vision, KPIs (key performance indicators), advanced potential technologies operation principles. Besides, reviewed modulation concentrating on Filter-Bank Multicarrier (FBMC) This ends by discussing applications challenges lessons identified from prior studies pave path research.

Язык: Английский

---