Multispectral Research Articles

Analysis of Bathymetry Accuracy Using Sentinel 2 Satellite on Different Characteristics Waters in Bali Island

Bathymetry surveys today are often carried out using the echo-sounding method, but this method has disadvantages, such as requiring a lot of time and being quite expensive. Along with the development of technology, some alternative methods can be used to visualize bathymetry, such as remote sensing. Remote Sensing uses satellite imagery in the operation, while the technique to acquire bathymetry is called Satellite-Derived Bathymetry (SDB). This method uses an optical satellite with several color bands or multispectral images. In this research, a satellite used to map ocean depth is Sentinel-2. The SDB technique used in this research is the Lyzenga Algorithm. The Lyzenga algorithm uses multilinear logarithms in its operation and can be used using three optical image channels (blue, green, and red channels). Supported by the SDB algorithm, an analysis of research locations was carried out at several points in the waters of Bali Island due to the diversity of water characteristics such as sea depth and wave height. From several analysis results of different characteristic waters in Bali Island, We can see that many parameters impact the result of the Satellite to visualize bathymetry. The Satellite's optimal result for reading the bathymetry depth is approximately 30 meters. But in reality, some cases can interfere with the accuracy of Satellite visualizing bathymetry within this depth. Breaking waves, high water sedimentation, and some objects that could guide the Satellite to misread them as elevation.

Urban sustainability in social housing environments: A spatial impact assessment in Bogotá, Colombia

As cities adapt to the challenges of rapid urbanization, sustainable development goals, and post-pandemic realities, understanding the intricacies of urban sustainability is vital. This study presents a spatial impact assessment of urban sustainability, focusing on the distinctive requirements of social housing urban environments in Bogota, Colombia. By contextualizing this study in the ever-evolving post-pandemic paradigm, it depicts the current conditions of the city towards future development scenarios. The sustainability assessment relies on a set of 11 Key Performance Indicators (KPIs), emphasizing the particular needs of social housing and offering a comprehensive analysis that links the conditions of the urban environment, environmental quality, and social well-being, all under the umbrella of Sustainable Development Goal 11. Specific spatial analysis using GIS tools (e.g. spatial interpolation, network analysis, multispectral imagery analysis), statistical analysis, and data engineering were employed to evaluate the selected KPIs. This evaluation revealed distinct spatial patterns of socioeconomic inequity, primarily impacting areas with a higher concentration of social housing within the city. These findings highlight critical areas requiring strategic attention to promote the city's sustainability transition. Key insights indicate that areas lacking sufficient access to green spaces and essential urban services, alongside higher pollution levels, are associated with lower social well-being, reduced perceptions of security, and are characterized by high population density and a significant presence of social housing. These results, available on an interactive web-GIS app, underscore the imperative for policies and planning that not only address the provision of social housing but also ensure a sustainable built environment, shaping a sustainable, inclusive, safe, and resilient future. The methodology and insights presented in this study are also applicable and scalable to similar urban contexts globally.

Design and on-orbit performance evaluation of Ethiopian earth observation satellite multispectral optical imaging payload

The Ethiopian Earth observation micro-satellite was successfully launched into a sun-synchronous orbit equipped with an optical multispectral imaging payload system. This optical multispectral imaging payload camera weighs 1.4 kg with four spectral bands: RGB and NIR, each having a unique spectral range. Furthermore, it has a field of view of 7.4°×0.3°, a relative F-number of 9.8°, and a spectral range of 0.45∼0.9μm. The present article covers the design and on-orbit performance analysis of the ETRSS-1 electro-optical imaging payload system, which is based on the COTS compact and unobscured off-axis three-mirror anastigmatic system for high-resolution imaging. Additionally, selecting an appropriate imaging sensor, optomechanical architecture, and performance characteristics for optical instruments is investigated to evaluate spatial, spectral, and radiometric requirements and the payload’s on-orbit performance and capability.

Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model

Multi-Stage Feature Fusion of Multispectral and SAR Satellite Images for Seasonal Crop-Type Mapping at Regional Scale Using an Adapted 3D U-Net Model

Roof plane parsing towards LoD-2.2 building reconstruction based on joint learning using remote sensing images

Building models are important for urban studies. Remote sensing multi-spectral (MS) images are widely used for its rich semantic information. The lack of geometry features is fulfilled by introducing photogrammetry derived digital surface models (DSMs), resulting in pairs of DSMs and MS images. Utilizing such pairs and a convolutional neural network, level of detail (LoD) 2.2 building models, which contain roof planes and major roof elements (e.g. dormers), are reconstructed in this work. Leveraging both raster and vector predictions, 3-D building models with straight edges and sharp corners are obtained. The proposed two-stage method first extracts vectorized roof lines from pairs of DSMs and RGB images, followed by generation of detailed 2-D and 3-D polygonal building models. We conducted our experiments based on two datasets: a custom dataset in Landsberg am Lech in Germany, and an open dataset named Roof3D. For the custom dataset, our proposed model achieved mean average precision (mAP) for building roof vertices of 64.3% and for building roof lines of 54.5% at highest. Mean precision and recall for reconstructed 2-D building roof plane polygons are 52.2% and 54.7% respectively. For the Roof3D dataset, mAP is reported to be 25.3% and 12.4% for the extracted building roof lines and roof plane polygons respectively.

Deep spatial–spectral difference network with heterogeneous feature mutual learning for sea fog detection

Multispectral remote sensing image-based sea fog detection (SFD) is both important and challenging. Deep learning methods for SFD have become mainstream due to their powerful nonlinear learning capabilities and flexibility. However, existing methods have not fully utilized the physical difference priors in multispectral images (MSI) for SFD, making it difficult to skillfully capture the shape and appearance characteristics of sea fog, thus leading to uncertainties in SFD. We propose the spatial–spectral difference network (S2DNet), a deep encoding–decoding framework that merges inter-spectral and intra-spectral heterogeneous difference features. Specifically, inspired by physics-based difference threshold methods, we developed a physics-inspired inter-spectral difference module (PIDM) that combines feature-level difference with deep neural networks to capture the shape characteristics of sea fog. We designed the intra-spectral difference module (ISDM) using difference convolution to represent sea fog’s fine-grained and dynamic appearance information. Furthermore, inspired by multi-view learning, we propose heterogeneous feature mutual learning (HFML) that seeks robust representations by focusing on semantically invariant aspects within heterogeneous difference features, adapting to the dynamic nature of sea fog. HFML is achieved through global feature mutual learning using an adversarial procedure and local feature mutual learning supported by a novel information-theoretic objective function that links maximizing statistical correlation with expectation maximization. Experiments on two SFD datasets show that integrating physical difference priors into deep learning improves SFD. In both continuous temporal and high spatial resolution SFD tasks, S2DNet outperforms existing advanced deep learning methods. Moreover, S2DNet demonstrates stronger robustness under degraded remote sensing image conditions, highlighting its potential usefulness and practicality in real-world applications.

Spectral Index Derivation Based on Multi-Spectral Satellite Imagery for Apple and Pear Crop Classification

Spectral Index Derivation Based on Multi-Spectral Satellite Imagery for Apple and Pear Crop Classification

Breaking through clouds: A hierarchical fusion network empowered by dual-domain cross-modality interactive attention for cloud-free image reconstruction

Cloud obscuration undermines the availability of optical images for continuous monitoring in earth observation. Fusing features from synthetic aperture radar (SAR) has been recognized as a feasible strategy to guide the reconstruction of corrupted signals in cloud-contaminated regions. However, due to the different imaging mechanisms and reflection characteristics, the substantial domain gap between SAR images and optical images makes it a challenging problem to effectively perform cross-modality feature fusion. Although several SAR-assisted cloud removal methods have been proposed, most of them are often unable to achieve adequate information interaction between different modalities, which greatly limits the effectiveness and reliability of cross-modality fusion. In this paper, we proposed a novel hierarchical framework for cloud-free multispectral image reconstruction, which effectively integrates SAR and optical data by a dual-domain interactive attention mechanism. The overall encoder–decoder network is a W-shaped asymmetric structure with a two-branch encoder and one decoder. The encoder branches extract features from SAR images and optical images separately, while the decoder exploits multiscale residual block groups to expand the receptive field and multi-output strategy for reducing the training difficulty. The core cross-modality feature fusion module at the bottleneck adopts the dual-domain interactive attention (DDIA) mechanism which enhances the reciprocal infusion of SAR and optical features to encourage the reconstruction of spectral and structural information. Furthermore, features in the spatial and frequency domains are integrated to improve the effectiveness of the fusion process. To echo the overall network structure, the loss function is designed as a multiscale loss in dual domains. The proposed method can realize sufficient information communication and effective cross-modality fusion between SAR features and optical features. Extensive experiments on the SMILE-CR dataset and SEN12MS-CR dataset demonstrated that the proposed method can outperform the seven representative deep-learning comparative methods in terms of visual performance and quantitative accuracy.

Earth Observation Multi-Spectral Image Fusion with Transformers for Sentinel-2 and Sentinel-3 Using Synthetic Training Data

Earth Observation Multi-Spectral Image Fusion with Transformers for Sentinel-2 and Sentinel-3 Using Synthetic Training Data

Codex Climaci Rescriptus I

Abstract This article presents a fresh transcription of Codex Climaci Rescriptus I, a Christian Palestinian Aramaic manuscript from the Early Period (ca. 6th century), containing parts of Matthew’s Gospel and Mark’s Gospel. The transcription has been made from high resolution multi-spectral images. In addition, an extended introduction examines the codicology of the manuscript and its paratextual features.

Remote sensing for estimating genetic parameters of biomass accumulation and modeling stability of growth curves in alfalfa.

Multi-spectral imaging by unoccupied aerial vehicles provides a non-destructive, high throughput approach to measuring biomass accumulation over successive alfalfa (Medicago sativa L. subsp. sativa) harvests. Information from estimated growth curves can be used to infer harvest biomass and to gain insights into the relationship between growth dynamics and forage biomass stability across cuttings and years. In this study, multi-spectral imaging and several common vegetation indices were used to estimate genetic parameters and model growth of alfalfa cultivars to determine the longitudinal relationship between vegetation indices and forage biomass. Results showed moderate heritability for vegetation indices, with median plot level heritability ranging from 0.11-0.64, across multiple cuttings in three trials planted in Ithaca, NY, and Las Cruces, NM. Genetic correlations between the normalized difference vegetation index and forage biomass were moderate to high across trials, cuttings, and the timing of multi-spectral image capture. To evaluate the relationship between growth parameters and forage biomass stability across cuttings and environmental conditions, random regression modeling approaches were used to estimate the growth parameters of cultivars for each cutting and the variance in growth was compared to the variance in genetic estimates of forage biomass yield across cuttings. These analyses revealed high correspondence between stability in growth parameters and stability of forage yield. The results of this study indicate that vegetation indices are effective at modeling genetic components of biomass accumulation, presenting opportunities for more efficient screening of cultivars and new longitudinal modeling approaches that can provide insights into temporal factors influencing cultivar stability.

Comparative Analysis of Machine Learning Techniques and Data Sources for Dead Tree Detection: What Is the Best Way to Go?

In Central Europe, the extent of bark beetle infestation in spruce stands due to prolonged high temperatures and drought has created large areas of dead trees, which are difficult to monitor by ground surveys. Remote sensing is the only possibility for the assessment of the extent of the dead tree areas. Several options exist for mapping individual dead trees, including different sources and different processing techniques. Satellite images, aerial images, and images from UAVs can be used as sources. Machine and deep learning techniques are included in the processing techniques, although models are often presented without proper realistic validation.This paper compares methods of monitoring dead tree areas using three data sources: multispectral aerial imagery, multispectral PlanetScope satellite imagery, and multispectral Sentinel-2 imagery, as well as two processing methods. The classification methods used are Random Forest (RF) and neural network (NN) in two modalities: pixel- and object-based. In total, 12 combinations are presented. The results were evaluated using two types of reference data: accuracy of model on validation data and accuracy on vector-format semi-automatic classification polygons created by a human evaluator, referred to as real Ground Truth. The aerial imagery was found to have the highest model accuracy, with the CNN model achieving up to 98% with object classification. A higher classification accuracy for satellite imagery was achieved by combining pixel classification and the RF model (87% accuracy for Sentinel-2). For PlanetScope Imagery, the best result was 89%, using a combination of CNN and object-based classifications. A comparison with the Ground Truth showed a decrease in the classification accuracy of the aerial imagery to 89% and the classification accuracy of the satellite imagery to around 70%. In conclusion, aerial imagery is the most effective tool for monitoring bark beetle calamity in terms of precision and accuracy, but satellite imagery has the advantage of fast availability and shorter data processing time, together with larger coverage areas.

Evaluating the utility of combining high resolution thermal, multispectral and 3D imagery from unmanned aerial vehicles to monitor water stress in vineyards

PurposeHigh resolution imagery from unmanned aerial vehicles (UAVs) has been established as an important source of information to perform precise irrigation practices, notably relevant for high value crops often present in semi-arid regions such as vineyards. Many studies have shown the utility of thermal infrared (TIR) sensors to estimate canopy temperature to inform on vine physiological status, while visible-near infrared (VNIR) imagery and 3D point clouds derived from red–green–blue (RGB) photogrammetry have also shown great promise to better monitor within-field canopy traits to support agronomic practices. Indeed, grapevines react to water stress through a series of physiological and growth responses, which may occur at different spatio-temporal scales. As such, this study aimed to evaluate the application of TIR, VNIR and RGB sensors onboard UAVs to track vine water stress over various phenological periods in an experimental vineyard imposed with three different irrigation regimes.MethodsA total of twelve UAV overpasses were performed in 2022 and 2023 where in situ physiological proxies, such as stomatal conductance (gs), leaf (Ψleaf) and stem (Ψstem) water potential, and canopy traits, such as LAI, were collected during each UAV overpass. Linear and non-linear models were trained and evaluated against in-situ measurements.ResultsResults revealed the importance of TIR variables to estimate physiological proxies (gs, Ψleaf, Ψstem) while VNIR and 3D variables were critical to estimate LAI. Both VNIR and 3D variables were largely uncorrelated to water stress proxies and demonstrated less importance in the trained empirical models. However, models using all three variable types (TIR, VNIR, 3D) were consistently the most effective to track water stress, highlighting the advantage of combining vine characteristics related to physiology, structure and growth to monitor vegetation water status throughout the vine growth period.ConclusionThis study highlights the utility of combining such UAV-based variables to establish empirical models that correlated well with field-level water stress proxies, demonstrating large potential to support agronomic practices or even to be ingested in physically-based models to estimate vine water demand and transpiration.

Monitoring invasive exotic grass species in ecological restoration areas of the Brazilian savanna using UAV images

Identifying and monitoring invasive exotic grasses (IEG) is critical for the ecological restoration of grasslands and savannas, as they are the main barrier to the successful recovery of native grasslands and savannas. The integration of high-resolution remote sensing data, acquired through UAVs (Unmanned Aerial Vehicles), with machine learning algorithms is advancing restoration monitoring. The present study aimed to estimate IEG cover and identify plots with different invasive species dominance in ecological restoration areas in the Brazilian savanna. For ground truth, species cover estimates were carried out in plots through point-line intercept sampling. Then, the areas were classified according to the dominance of each invasive species (>40% vegetation cover) or of a mix of native species. A multispectral camera onboard a UAV was used to acquire images in the visible to near-infrared spectrum. From the images, vegetation indices and texture metrics were derived as predictor variables. The Random Forest (RF) algorithm was used to estimate the percentage of invasive species cover and to classify plots in terms of species dominance. The final RF regression for invasive species cover percentage presented an R2 of 0.71 and selected the blue band, NIR and Ratio Vegetation Index (RVI) as the most important variables. The overall accuracy of plot classification according to species dominance was 84%. The most prominent predictors were the Green Chlorophyll Index (GCI), the atmospherically resistant vegetation index (ARVI), and the RVI. The structural and photosynthetic characteristics of exotic and native species influenced the spectral responses. In conclusion, multispectral images acquired with UAV can be used to estimate the proportion of invasion in restoration sites and to map areas dominated by different invasive grass species in grasslands and savannas. This is a useful tool for evaluating restoration success and can help indicate areas that require management interventions.

Unveiling sequential layered heterogeneity in multi-spectral transmission images clustering through iterative terrace compression with adaptive neighborhoods analysis

Multi-spectral transmission imaging looks forward to an early breast cancer screening with cost-effectiveness, safety, and ease of use. However, the biological tissue of the breast owns scattering and strong absorption properties, resulting in transmission images with a low signal-to-noise ratio and prior investigation focused on detection heterogeneity within a single layer, but the different depths in heterogeneity due to the spherical shape of the breast causing the challenges. Accurately detecting heterogeneity in different layers is crucial due to low contrast, veiling layers, and unclear boundaries, which can be difficult to identify in clustering and segmentation. The breast heterogeneity identification can be handled by combining image processing techniques; nevertheless, considering labeling limits and data accessibility, the clustering algorithm provides an acceptable substitute. Therefore, the paper proposes a novel methodology integrating the iterative terrace compression method with adaptive neighborhoods analysis to identify sequential multi-layered heterogeneity and enhance the clustering of multi-spectral transmission images. Our experimental setup involved the collection of low grayscale images across six wavelengths, followed by advanced image processing techniques, including frame accumulation to improve image signal-to-noise ratio and then polynomial surface fitting to eliminate trend items from uneven light. After that, iterative terrace compression with adaptive neighborhoods analysis is applied to reduce redundancy and unveil heterogeneity in different layers and window functions to remove unnecessary gray information. Finally, clustering combined with pseudo-color is used for clustering analysis and visual representation for aiding in heterogeneity detection. Results indicate a significant improvement in detection metrics, with our method outpacing existing techniques regarding the Dice coefficient, F1 score, and Jaccard. This innovative approach not only enhances the characterization of breast tissue heterogeneities in different layers but also promises practical clinical applications in breast cancer screening.

Yield Prediction Models for Rice Varieties Using UAV Multispectral Imagery in the Amazon Lowlands of Peru

Rice is cataloged as one of the most widely cultivated crops globally, providing food for a large proportion of the global population. Integrating Geographic Information Systems (GISs), such as unmanned aerial vehicles (UAVs), into agricultural practices offers numerous benefits. UAVs, equipped with imaging sensors and geolocation technology, enable precise crop monitoring and management, enhancing yield and efficiency. However, Peru lacks sufficient experience with the application of these technologies, making them somewhat unfamiliar in the context of modern agriculture. In this study, we conducted experiments involving four distinct rice varieties (n = 24) at various stages of growth to predict yield using vegetation indices (VIs). A total of nine VIs (NDVI, GNDVI, ReCL, CIgreen, MCARI, SAVI, CVI, LCI, and EVI) were assessed across four dates: 88, 103, 116, and 130 days after sowing (DAS). Pearson correlation analysis, principal component analysis (PCA), and multiple linear regression were used to build prediction models. The results showed a general prediction model (including all the varieties) with the best performance at 130 days after sowing (DAS) using NDVI, EVI, and SAVI, with a coefficient of determination (adjusted-R2 = 0.43). The prediction models by variety showed the best performance for Esperanza at 88 DAS (adjusted-R2 = 0.94) using EVI as the vegetation index. The other varieties showed their best performance using different indices at different times: Capirona (LCI and CIgreen, 130 DAS, adjusted-R2 = 0.62); Conquista Certificada (MCARI, 116 DAS, R2 = 0.52); and Conquista Registrada (CVI and LCI, 116 DAS, adjusted-R2 = 0.79). These results provide critical information for optimizing rice crop management and support the use of unmanned aerial vehicles (UAVs) to inform timely decision making and mitigate yield losses in Peruvian agriculture.

Geospatial Mapping and Detection of Ferrous, Iron Oxides, and Clay Minerals in District Mohmand, Pakistan

The study focuses on the utilization of remote sensing techniques to effectively identify and detect ferrous,iron oxides, and clay minerals in Mohmand district, Pakistan, using LANDSAT 8 multispectral images. This studyfocuses on the increasing demand and importance of these minerals in mining and commercial activities. Mineralexploration in Mohmand district, utilizing remote sensing technology to identify mineral compositions using the bandratio is done. This technique allows for a more focused and precise approach to exploration and extraction techniques.Cloud-free LANDSAT 8 images with minimal vegetation cover were utilized for the analysis. The band ratio approachwas utilized to identify areas exhibiting diverse mineral compositions. The study highlights the effectiveness of thesuggested methodology in mapping and detecting ferrous, iron oxides, and clay minerals, indicating the significantpotential of remote sensing for mineral exploration. The results highlight the importance of developing distributionmaps to support more efficient methods for mining and mineral exploration. The study contributes to a more focusedand efficient assessment of mineral resources and extraction techniques in the Mohmand district and similar geologicalterrains, offering stakeholders a valuable tool for informed decision-making in mineral exploration and exploitationefforts.

Monitoring of parasite Orobanche cumana using Vis-NIR hyperspectral imaging combining with physio-biochemical parameterson host crop Helianthus annuus.

This study provided a non-destructive detection method with Vis-NIR hyperspectral imaging combining with physio-biochemical parameters in Helianthus annuus in response to Orobanche cumana infection that took insights into the monitoring of sunflower weed. Sunflower broomrape (Orobanche cumana Wallr.) is an obligate weed that attaches to the host roots of sunflower (Helianthus annuus L.) leading to a significant reduction in yield worldwide. The emergence of O. cumana shoots after its underground life-cycle causes irreversible damage to the crop. In this study, a fast visual, non-invasive and precise method for monitoring changes in spectral characteristics using visible and near-infrared (Vis-NIR) hyperspectral imaging (HSI) was developed. By combining the bands sensitive to antioxidant enzymes (SOD, GR), non-antioxidant enzymes (GSH, GSH + GSSG), MDA, ROS (O2-, OH-), PAL, and PPO activities obtained from the host leaves, we sought to establish an accurate means of assessing these changes and conducted imaging acquisition using hyperspectral cameras from both infested and non-infested sunflower cultivars, followed by physio-biochemical parameters measurement as well as analyzed the expression of defense related genes. Extreme learning machine (ELM) and convolutional neural network (CNN) models using 3-band images were built to classify infected or non-infected plants in three sunflower cultivars, achieving accuracies of 95.83% and 95.83% for the discrimination of infestation as well as 97.92% and 95.83% of varieties, respectively, indicating the potential of multi-spectral imaging systems for early detection of O. cumana in weed management.

Capability of space borne multispectral image for detecting discoloration in optically complex coastal waters

Coastal pollutants, from harmful algal blooms, sewage and industrial discharges, pose severe risks to marine ecosystems and public health. Recently, Promenade Beach in Puducherry, Southeast-India, experienced reddish-brown water discoloration, suspected to result from either algal blooms or suspended matter. This study monitored the spatial extent and characteristics of the discoloration using Sentinel-2 satellite images from September to November 2023, with field observations and laboratory analyses. Analyses included measurements of chlorophyll-a (Chl-a), Total Suspended Matter (TSM), and the Normalized Difference Chlorophyll Index (NDCI) to differentiate between algal blooms and other pollutants. The satellite data indicated extents of discoloration, with high TSM concentrations (>45 g/m3) and negative NDCI values suggesting absence of algal blooms. No mortality of aquatic organisms was observed during this discoloration, indicating no deleterious impact on aquatic life. This approach highlights the importance of combining satellite technology with field data for effective coastal pollution monitoring, essential for protecting marine ecosystems.

Estimation of macro and micronutrient concentrations in ‘valencia’ orange leaves at different phenological stages using multispectral image analysis and multiple regression

ABSTRACT This study aimed at estimating the macro- and micronutrient concentrations in leaves of Valencia oranges (Citrus sinensis [L.] Osbeck) through multiple regression analysis using multispectral images and vegetation indices (VIs) selected through the stepwise regression method. The data were collected in a commercial orchard of Valencia oranges in El Barretal, Tamaulipas, Mexico. The leaf samples were analysed in a laboratory to determine the concentrations of N, P, K, Ca, Mg, Cu, Fe, Mn, and Zn using traditional chemical methods; the relative chlorophyll values were obtained using a chlorophyll metre (SPAD502 Plus). Multi-spectral images of the tree canopy were acquired using a UAV equipped with a multispectral camera with five wavelengths (blue, green, red, red edge, and near-infrared); based on these data, 85 VIs were calculated. To select the predictor variables that were most relevant for the model, 90 candidate variables were divided into three groups with 30 VIs grouped by nutrients based on the highest and lowest absolute values found in the correlation matrix. Heteroscedasticity and autocorrelation were also assessed through the Breusch-Pagan and Durbin-Watson tests, respectively. The selected variables were used in multiple regression analysis. The resulting models were validated by mean absolute error (MAE), root-mean-square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination ( R 2 ). The prediction models showed satisfactory results, with values R 2 between 0.79 and 0.95 and relatively low (<10) MAE and RMSE for all nutrients, except Fe ( < 30 ) in all phenological stages; MAPE values were lower than 0.5% for all nutrients. This study showed that multispectral imaging combined with multiple regression analysis effectively predicts nutrient levels in the leaves of Valencia oranges in various phenological stages. This study presents a new perspective on agricultural systems, offering an effective alternative to assess the nutritional conditions of crops.