Multispectral Data Research Articles

On the fusion between interferometric satellite data and in situ measurements for the monitoring of built heritage

Over the past decades, earthquakes, and other catastrophic events has highlighted the increasingly growing vulnerability of infrastructures, buildings, and architectural heritage structures. In addition to catastrophic events, often related to climate change, another fundamental aspect is represented by the lack of maintenance and monitoring of the asset. In the field of preservation of buildings and infrastructures, Structural Health Monitoring techniques can effectively contribute to the assessment of the health state of structures. In the case of structural monitoring using data-driven approaches, since the information depends on the type of data used, a great resource for knowing as much as possible about the structure is represented by the combination of multiple data. Thanks to the integration of different types of data, it is possible to know the conditions of the structure in more detail as different aspects can be combined. In this context, together with the data obtained from in situ monitoring systems, data obtained remotely, i.e. satellite data, can be used. There are different types of satellite data that can be used to study different aspects, e.g., multispectral data, hyperspectral data, and interferometric data, and they can make different contribution to civil engineering. In this paper, the exploitability of open-source interferometric data is investigated and they are studied for the purpose of their integration with data obtained from a monitoring system installed on a monumental building, in order to monitor and observe structural health.

The structures control the evolution of molasse basins and alteration zones occurrences in the northwestern sector of the Central Eastern Desert of Egypt

Integration between the analyses of both fieldwork and remote sensing dataset were employed to assess the structural evolution of molasse basins and explore gold mineral deposits in the El Qash area, Central Eastern Desert of Egypt. Sandstone, mudstones, wacke, and pebbly conglomerates make up most of the sediments in the molasse basins. The younger basins (595–575 Ma) are small, less weathered, and mostly Dokhan detritus-filled basins compared to the larger older basins (> 625–605 Ma), which have more weathered sources mainly of arc metavolcanics. The molasse basins appear to have originated in a north–south regional extensional setting, characterized by a prolonged period of left-lateral transtension combined with the formation of NNE-trending synformal folds during an ENE–WSW compression phase. Notably, en-echelon arrays of normal faults, oriented perpendicular to the boundary of the strike-slip shear zone, are a recurring feature in basins formed through transtension. Furthermore, oblique NE-SW compression played a role in generating SW-dipping thrust faults and regional folding with NW–SE orientation, along with the reactivation of transtensional normal faults in a reverse manner. Multispectral satellite imagery data and radar data are used to map the relevant lithological units, structures, and hydrothermal alteration zones. This study concludes that the regions where gold deposits may be explored in connection with prospecting alteration minerals include the area around the ophiolitic assemblages, and the granitic intrusions, in addition to the felsite and the molasse sediments contacts.

دراسة مقارنة التعلم الآلي في التصنيف الفعال للبيانات متعددة الأطياف في الزراعة

يتطلب أن تكون خرائط محاصيل موثوقة ودقيقة لتحقيق الأمن الغذائي من المستوى الإقليمي إلى المستوى العالمي. يؤدي التوفر المتزايد لصور الأقمار الصناعية إلى مشكلة "البيانات الضخمة" أثناء إنتاج خرائط المحاصيل. الآن، اكتسبت المنصات السحابية الكثير من الاهتمام لتصنيف المحاصيل في مناطق واسعة. الهدف الرئيسي من البحث هو تحليل تصنيف المحاصيل باستخدام مختلف التعلم الآلي (ML) مثل آلة دعم المتجهات (SVM)، وتعزيز شجرة التدرج (GTB)، والغابات العشوائية (RF)، وشجرة القرار (DT) بالإضافة إلى التصنيف والتصنيف. أشجار الانحدار (CART) على منصة محرك Goggle Earth. الهدف هو استكشاف كفاءة محرك Google Earth (GEE) عند تصنيف المحاصيل المختلفة باستخدام مجموعات البيانات متعددة الأطياف من Sentinel 2 MSI بالإضافة إلى الأقمار الصناعية Landsat 8 OLI لرسم خرائط المحاصيل في منطقة ماثورا في ولاية أوتار براديش بالهند. تم استخدام أفضل صورة خالية من السحابة (أقل من 5%) لمجموعات بيانات Landsat 8 OLI وSentinel 2 MSI ("2020-12-26"، و"2020-12-30") لتصنيف المحاصيل بمساعدة التصفية التلقائية، أي النسبة المئوية. الملكية السحابية على منصات GEE. علاوة على ذلك، يمكن تنظيم أداء منصة GEE والحصول عليها وتوضيحها وكذلك معالجتها المسبقة لمجموعة بيانات الأقمار الصناعية بقوة كبيرة. تم استخدام النقاط كمساحات مميزة مثل مجموعات بيانات التدريب. علاوة على ذلك، يتم استخدام مصفوفات الارتباك لتقييم الدقة (دقة المنتج والمستخدم) ومعامل كابا. بالإضافة إلى ذلك، قم بمقارنة نتائج مجموعة البيانات (Sentinel 2 MSI وLandsat 8 OLI) على أساس الدقة الإجمالية (OA) ودرجة F1 بالإضافة إلى معامل كابا. تم العثور على أعلى وصول حر باستخدام GTB (86.7%) يليه RF (82.5%)، CART (81.0%)، DT (78.1%) وSVM (66.5%) لصورة Landsat 8 OLI. بالنسبة لصورة Sentinel 2، حققت GTB أعلى وصول وصول بنسبة 84.2% يليها SVM (84%)، RF (82.3%)، DT (75.2%)، وCART (75.0%) على التوالي. على أساس البحث، وجد أن أداء GTB كان جيدًا بين جميع المصنفات في رسم خرائط المحاصيل باستخدام مجموعتي البيانات متعددة الأطياف.

A dataset of UAV multispectral images for a banana Fusarium wilt survey

Banana Fusarium wilt, also known as "banana cancer", currently poses a significant threat to banana production worldwide. Timely and accurate identification of Fusarium wilt disease is crucial for effective disease control and optimizing agricultural planting structure. To explore the use of unmanned aerial vehicle (UAV) remote sensing for identifying banana wilt disease, in this study, we obtained comprehensive experimental data on wilted banana plants in a banana plantation in Long'an County, Guangxi. The dataset includes UAV multispectral reflectance data and ground survey data on the incidence of banana wilt disease. The UAV multispectral imagery was acquired under clear, cloud-free, and well-illuminated weather conditions, at a flying altitude of 120 meters with a spatial resolution of 8 cm/pixel. The ground sample points survey on the occurrence of banana wilt disease was conducted using a high-precision handheld GPS unit to collect latitude and longitude information for each sample point, and the positions were matched with the corresponding center positions of banana plants in the UAV imagery indoors. The dataset provides high- spatial-resolution UAV multispectral imagery data and accurate ground sample point survey data. It can be applied in the research and monitoring of UAV remote sensing identification and surveillance of banana wilt disease. It plays a crucial role in advancing research and application of remote sensing monitoring for agricultural crop diseases.

A dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020

Being a major tea producing province in China, Fujian Province is badly in need of quick and accurate spatial distribution of tea plantation for decision-making in both the agricultural economic development and the ecological environment construction for the province. This study retrieved and processed Sentinel-1 (S1) radar data and Sentinel-2 (S2) multispectral data on the GEE cloud platform; and it extracted 98 features, such as spectral features, texture features, and terrain features from the terrain data. The recursive elimination support vector machine algorithm (SVM RFE) is used to screen the characteristic variables, resulting in the creation of 4 feature combination schemes. Using a support vector machine (SVM) classifier to extract the distribution data of tea plantations and assessing the accuracy of the 4 feature combination schemes, we obtained the spatial distribution data of tea plantations at 10 m resolution in Fujian Province in 2020. On this basis, we used the GEE cloud platform to access the vegetation disturbance information in Fujian Province from 2000 to 2020. We finally obtained a dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020 by excluding the non-tea plantation areas from the images between 2000 and 2015 with the mask generated from the 2020 tea garden extraction results. This dataset has been manually validated using sample points from key tea-producing counties and townships. The results indicate an extraction accuracy of over 92% for tea plantations in 2020. The extraction accuracy of tea plantations obtained using interference data removal method in 2000, 2005, 2010, and 2015 was all above 80%. The dataset with a high accuracy in tea plantation extraction can provide support for relevant departments in tea plantation management.

Developing a Semi-Automated Near-Coastal, Water Quality-Retrieval Process from Global Multi-Spectral Data: South-Eastern Australia

The estimation of water quality properties through satellite remote sensing relies on (1) the optical characteristics of the water body, (2) the resolutions (spatial, spectral, radiometric and temporal) of the sensor and (3) algorithm(s) applied. More than 80% of global water bodies fall under Case I (open ocean) waters, dominated by scattering and absorption associated with phytoplankton in the water column. Globally, previous studies show significant correlations between satellite-based retrieval methods and field measurements of absorbing and scattering constituents, while limited research from Australian coastal water bodies appears. This study presents a methodology to extract chlorophyll a properties from surface waters from near-coastal environments, within 2 km of coastline, in Tasmania, south-eastern Australia. We use general purpose, global, long-time series, multi-spectral satellite data, as opposed to ocean colour-specific sensor data. This approach may offer globally applicable tools for combining global satellite image archives with in situ field sensors for water quality monitoring. To enable applications from local to global scales, a cloud-based geospatial analysis workflow was developed and tested on several sites. This work represents the initial stage in developing a semi-automated near-coastal water-quality workflow using easily accessed, fully corrected global multi-spectral datasets alongside large-scale computation and delivery capabilities. Our results indicated a strong correlation between the in situ chlorophyll concentration data and blue-green band ratios from the multi-spectral sensor. In line with published research, environment-specific empirical models exhibited the highest correlations between in situ and satellite measurements, underscoring the importance of tailoring models to specific coastal waters. Our findings may provide the basis for developing this workflow for other sites in Australia. We acknowledge the use of general purpose multi-spectral data such as the Sentinel-2 and Landsat Series, their corrections and algorithms may not be as accurate and precise as ocean colour satellites. The data we are using are more readily accessible and also have true global coverage with global historic archives and regular, global collection will continue at least 10 years in the future. Regardless of sensor specifications, the retrieval method relies on localised algorithm calibration and validation using in situ measurements, which demonstrates close-to-realistic outputs. We hope this approach enables future applications to also consider these globally accessible and regularly updated datasets that are suited to coastal environments.

Long-term annual estimation of forest above ground biomass, canopy cover, and height from airborne and spaceborne sensors synergies in the Iberian Peninsula

The Mediterranean Basin has experienced substantial land use changes as traditional agriculture decreased and population migrated from rural to urban areas, which have resulted in a large forest cover increase. The combination of Landsat time series, providing spectral information, with lidar, offering three-dimensional insights, has emerged as a viable option for the large-scale cartography of forest structural attributes across large time spans. Here we develop and test a comprehensive framework to map forest above ground biomass, canopy cover and forest height in two regions spanning the most representative biomes in the peninsular Spain, Mediterranean (Madrid region) and temperate (Basque Country). As reference, we used lidar-based direct estimates of stand height and forest canopy cover. The reference biomass and volume were predicted from lidar metrics. Landsat time series predictors included annual temporal profiles of band reflectance and vegetation indices for the 1985–2023 period. Additional predictor variables including synthetic aperture radar, disturbance history, topography and forest type were also evaluated to optimize forest structural attributes retrieval. The estimates were independently validated at two temporal scales, i) the year of model calibration and ii) the year of the second lidar survey. The final models used as predictor variables only Landsat based metrics and topographic information, as the available SAR time-series were relatively short (1991–2011) and disturbance information did not decrease the estimation error. Model accuracies were higher in the Mediterranean forests when compared to the temperate forests (R2 = 0.6–0.8 vs. 0.4–0.5). Between the first (1985–1989) and the last (2020–2023) decades of the monitoring period the average forest cover increased from 21 ± 2% to 32 ± 1%, mean height increased from 6.6 ± 0.43 m to 7.9 ± 0.18 m and the mean biomass from 31.9 ± 3.6 t ha−1 to 50.4 ± 1 t ha−1 for the Mediterranean forests. In temperate forests, the average canopy cover increased from 55 ± 4% to 59 ± 3%, mean height increased from 15.8 ± 0.77 m to 17.3 ± 0.21m, while the growing stock volume increased from 137.8 ± 8.2 to 151.5 ± 3.8 m3 ha−1. Our results suggest that multispectral data can be successfully linked with lidar to provide continuous information on forest height, cover, and biomass trends.

Open Remote Sensing Data in Digital Soil Organic Carbon Mapping: A Review

This review focuses on digital soil organic carbon (SOC) mapping at regional or national scales in spatial resolutions up to 1 km using open data remote sensing sources, emphasizing its importance in achieving United Nations’ Sustainable Development Goals (SDGs) related to hunger, climate action, and land conservation. The literature review was performed according to scientific studies indexed in the Web of Science Core Collection database since 2000. The analysis reveals a steady rise in total digital soil mapping studies since 2000, with digital SOC mapping studies accounting for over 20% of these studies in 2023, among which SDGs 2 (Zero Hunger) and 13 (Climate Action) were the most represented. Notably, countries like the United States, China, Germany, and Iran lead in digital SOC mapping research. The shift towards machine and deep learning methods in digital SOC mapping has surged post-2010, necessitating environmental covariates like topography, climate, and spectral data, which are cornerstones of machine and deep learning prediction methods. It was noted that the available climate data primarily restrict the spatial resolution of digital SOC mapping to 1 km, which typically requires downscaling to harmonize with topography (up to 30 m) and multispectral data (up to 10–30 m). Future directions include the integration of diverse remote sensing data sources, the development of advanced algorithms leveraging machine learning, and the utilization of high-resolution remote sensing for more precise SOC mapping.

Crop aboveground biomass monitoring model based on UAV spectral index reconstruction and Bayesian model averaging: A case study of film-mulched wheat and maize

Aboveground biomass (AGB) directly reflects crop carbon fixation capacity. Utilizing unmanned aerial vehicle (UAV) remote sensing for high-throughput AGB monitoring offers benefits to agricultural management and food production. This study aimed to develop a method for monitoring AGB in film-mulched crops using UAV multispectral data. A three-year field experiment was conducted using wheat (Exps. 1 and 2 in 2021–2022, and Exps. 5 and 6 in 2022–2023) and maize (Exps. 3 and 4) with varying cropping patterns. Spectral indices (SIs) of different feature reflectances (e.g., vegetation, soil, and mulch pixels) were reconstructed using least absolute shrinkage and selection operator methods. The Bayesian model averaging (BMA) method integrated seven independent machine learning algorithms to construct a Bayesian ensemble model (BEM). The results demonstrated that spectral index reconstruction (SIR) enhanced the correlation between SIs and AGB, while BMA reduced model uncertainty and improved AGB prediction accuracy. The BEM model, based on Exps. 1 and 2 datasets, achieved determination coefficients of 0.78–0.84 and root mean square error (RMSE) of 0.81–0.89 t ha−1. Model validation across years and crops demonstrated the generalization of the SIR + BEM method for AGB estimation. The RMSEs of the model inter-annual transport predictions were 0.83 and 0.93 t ha−1 in Exps. 5 and 6, respectively, and RMSE of the predictions between crops was 1.43 t ha−1 for the maize dataset (Exps. 3 + 4). The approach proposed in this study has great potential for monitoring growth status of film-mulched crops at the farm scale and providing guidance for precision agriculture management.

Evaluation of Machine Learning Regression Techniques for Estimating Winter Wheat Biomass Using Biophysical, Biochemical, and UAV Multispectral Data

Crop above-ground biomass (AGB) estimation is a critical practice in precision agriculture (PA) and is vital for monitoring crop health and predicting yields. Accurate AGB estimation allows farmers to take timely actions to maximize yields within a given growth season. The objective of this study is to use unmanned aerial vehicle (UAV) multispectral imagery, along with derived vegetation indices (VI), plant height, leaf area index (LAI), and plant nutrient content ratios, to predict the dry AGB (g/m2) of a winter wheat field in southwestern Ontario, Canada. This study assessed the effectiveness of Random Forest (RF) and Support Vector Regression (SVR) models in predicting dry ABG from 42 variables. The RF models consistently outperformed the SVR models, with the top-performing RF model utilizing 20 selected variables based on their contribution to increasing node purity in the decision trees. This model achieved an R2 of 0.81 and a root mean square error (RMSE) of 149.95 g/m2. Notably, the variables in the top-performing model included a combination of MicaSense bands, VIs, nutrient content levels, nutrient content ratios, and plant height. This model significantly outperformed all other RF and SVR models in this study that relied solely on UAV multispectral data or plant leaf nutrient content. The insights gained from this model can enhance the estimation and management of wheat AGB, leading to more effective crop yield predictions and management.

Application of Normalized Radar Backscatter and Hyperspectral Data to Augment Rangeland Vegetation Fractional Classification

Rangeland ecosystems in the western United States are vulnerable to climate change, fire, and anthropogenic disturbances, yet classification of rangeland areas remains difficult due to frequently sparse vegetation canopies that increase the influence of soils and senesced vegetation, the overall abundance of senesced vegetation, heterogeneity of life forms, and limited ground-based data. The Rangeland Condition Monitoring Assessment and Projection (RCMAP) project provides fractional vegetation cover maps across western North America using Landsat imagery and artificial intelligence from 1985 to 2023 at yearly time-steps. The objectives of this case study are to apply hyperspectral data from several new data streams, including Sentinel Synthetic Aperture Radar (SAR) and Earth Surface Mineral Dust Source Investigation (EMIT), to the RCMAP model. We run a series of five tests (Landsat-base model, base + SAR, base + EMIT, base + SAR + EMIT, and base + Landsat NEXT [LNEXT] synthesized from EMIT) over a difficult-to-classify region centered in southwest Montana, USA. Our testing results indicate a clear accuracy benefit of adding SAR and EMIT data to the RCMAP model, with a 7.5% and 29% relative increase in independent accuracy (R2), respectively. The ability of SAR data to observe vegetation height allows for more accurate classification of vegetation types, whereas EMIT’s continuous characterization of the spectral response boosts discriminatory power relative to multispectral data. Our spectral profile analysis reveals the enhanced classification power with EMIT is related to both the improved spectral resolution and representation of the entire domain as compared to legacy Landsat. One key finding is that legacy Landsat bands largely miss portions of the electromagnetic spectrum where separation among important rangeland targets exists, namely in the 900–1250 nm and 1500–1780 nm range. Synthesized LNEXT data include these gaps, but the reduced spectral resolution compared to EMIT results in an intermediate 18% increase in accuracy relative to the base run. Here, we show the promise of enhanced classification accuracy using EMIT data, and to a smaller extent, SAR.

Использование данных дистанционного зондирования Земли для анализа межгодовой динамики площади Тениз-Коргалжынских озер

The Teniz-Korgalzhyn lake system has the status of an international Ramsar site and is the most important ornithological center in Central Asia. It includes more than 60 shallow fresh- and salt water bodies among which the largest salt ones are Big and Small Teniz and a group of fresh Korgalzhyn lakes. Fluctuations in water levels there and changes in their area determine the degree of favorable habitat conditions for key ornithological species. A quantitative assessment of the water levels’ interannual dynamics in 2006–2019 was carried out using remote sensing and geoinformation mapping methods. The choice of the methodology to use multispectral data for water surface area study is substantiated. Calculations are made, and a corresponding map of the bodies’ water surface area dynamics is compiled. Four periods with multidirectional dynamics of changes in it were identified. They are caused by both natural and anthropogenic factors and differ in intensity for fresh and salt lakes. Fluctuations of fresh Korgalzhyn ones are mostly associated with natural and climatic impact. Salty Big and Small Teniz are characterized by more significant changes in water surface the area, caused primarily by human activities, including periodic breakthroughs of retaining dams. Maximum deviations towards the increase were noted for fresh ones in 2016–2019, and for saline in 2014–2019. The observed decrease in the total area of the water surface in the period from 2006 to 2013 was mainly associated with the Small and Big Teniz

Rock glaciers as proxy for machine learning based debris‐covered glacier mapping of Kinnaur District, Himachal Pradesh

AbstractThis research introduces an innovative approach by utilising rock glaciers (RGs) as a proxy for mapping debris‐covered glaciers (DCGs). This approach focuses on the interconnected nature of glaciers, DCGs and RGs in a continuum where DCGs can transform into RGs over time due to various processes. This study utilises six machine learning models—logistic regression (LR), support vector machine (SVM), K‐nearest neighbour (KNN), Naïve Bayes (NB), decision tree (DT) and random forest (RF)—combined with multispectral satellite data (Sentinel‐2 and Landsat 8) and topographical data derived from ALOS PALSAR DEM. Performance metrics such as accuracy, area under the curve (AUC) score, precision, recall and F1‐score were evaluated to assess model performance. This detailed mapping provides a precise estimation of the extent of DCGs in the Kinnaur district. The estimated DCG areas revealed intriguing variation across models, with RF (9.71%), KNN (9.67%) and NB (9.41%) yielding similar predictions. SVM (11.61%) projected a slightly larger DCG area, whereas DT (5.54%) and LR (25.55%) provided contrasting results. Validation against high‐resolution satellite images, Google Earth images and glacier inventories confirmed the accuracy and reliability of our approach. Based on our findings for our specific study, the most effective method for mapping DCGs is RF, followed by KNN, NB, DT and SVM. The combination of machine learning models and RG data presents a novel and promising approach to remote sensing‐based DCG mapping, with potential applications for other regions and broader environmental studies.

A fast spectral recovery does not necessarily indicate post-fire forest recovery

BackgroundClimate change has increased wildfire activity in the western USA and limited the capacity for forests to recover post-fire, especially in areas burned at high severity. Land managers urgently need a better understanding of the spatiotemporal variability in natural post-fire forest recovery to plan and implement active recovery projects. In burned areas, post-fire “spectral recovery”, determined by examining the trajectory of multispectral indices (e.g., normalized burn ratio) over time, generally corresponds with recovery of multiple post-fire vegetation types, including trees and shrubs. Field data are essential for deciphering the vegetation types reflected by spectral recovery, yet few studies validate spectral recovery metrics with field data or incorporate spectral recovery into spatial models of post-fire vegetation recovery. We investigated relationships between spectral recovery and field measurements of post-fire recovery (16 to 27 years post-fire) from 99 plots in mixed conifer forests of the Blue Mountains, USA. Additionally, using generalized linear mixed effects models, we assessed the relative capacities of multispectral, climatic, and topographic data to predict field measurements of post-fire recovery.ResultsWe found that a fast spectral recovery did not necessarily coincide with field measurements of forest recovery (e.g., density of regenerating seedlings, saplings, and young trees and % juvenile conifer cover). Instead, fast spectral recovery often coincided with increases in % shrub cover. We primarily attributed this relationship to the response of snowbrush ceanothus, an evergreen shrub that vigorously resprouts post-fire. However, in non-trailing edge forests—where it was cooler and wetter and fast-growing conifers were more common—rapid spectral recovery coincided with both increases in % shrub cover and forest recovery. Otherwise, spectral recovery showed potential to identify transitions to grasslands, as grass-dominated sites showcased distinctly slow spectral trajectories. Lastly, field measurements of post-fire forest recovery were best predicted when including post-fire climate and multispectral data in predictive models.ConclusionsDespite a disconnect between a fast spectral recovery and forest recovery, our results suggest that including multispectral data improved models predicting the likelihood of post-fire forest recovery. Improving predictive models would aid land managers in identifying sites to implement active reforestation projects.Graphical Photo credit: J. Celebrezze

UAV data and deep learning: efficient tools to map ant mounds and their ecological impact

AbstractHigh‐resolution unoccupied aerial vehicle (UAVs) data have alleviated the mismatch between the scale of ecological processes and the scale of remotely sensed data, while machine learning and deep learning methods allow new avenues for quantification in ecology. Ant nests play key roles in ecosystem functioning, yet their distribution and effects on entire landscapes remain poorly understood, in part because they and their mounds are too small for satellite remote sensing. This research maps the distribution and impact of ant mounds in a 20 ha treeline ecotone. We evaluate the detectability from UAV imagery using a deep learning model for object detection and different combinations of RGB, thermal and multispectral sensor data. We were able to detect ant mounds in all imagery using manual detection and deep learning. However, the highest precision rates were achieved by deep learning using RGB data which has the highest spatial resolution (1.9 cm) at comparable UAV flight height. While multispectral data were outperformed for detection, it allows for novel insights into the ecology of ants and their spatial impact on vegetation productivity using the normalized difference vegetation index. Scaling up, this suggests that ant mounds quantifiably impact vegetation productivity for up to 4% of our study area and up to 8% of the Betula nana vegetation communities, the vegetation type with the highest abundance of ant mounds. Therefore, they could have an overlooked role in nutrient‐limited tundra vegetation, and on the shrubification of this habitat. Further, we show the powerful combination UAV multi‐sensor data and deep learning for efficient ecological tracking and monitoring of mound‐building ants and their spatial impact.

Comparison of Deep and Machine Learning Approaches for Quebec Tree Species Classification Using a Combination of Multispectral and LiDAR Data

Accessing tree species information is required for making appropriate decisions in forest management. 3D photo-interpretation using high spatial resolution aerial imagery is used to provide information on tree species in the province of Quebec. However, the shortage of qualified interpreters and the increasing costs of 3D photo-interpretation have affected the production of the forest inventory. In this study, we employed deep and machine learning models to classify nine tree species (i.e., paper birch, yellow birch, red maple, poplar, black spruce, white spruce, tamarack, jack pine, and balsam fir). We used a combination of spectral and vertical structural information extracted from 30-cm aerial imagery and airborne light detection and ranging (LiDAR) data in a 9 , 100 km 2 forested area in Quebec, Canada. The results indicated that Dense Convolution Network (DenseNet) achieved the best overall accuracy of 78%, outperforming machine learning methods by 5%. In addition, the models’ performance was independently assessed using permanent and temporary ground sample plots, acknowledging the superiority of DenseNet in terms of overall accuracy (73%) in predicting the dominant species. Our results suggest that the combination of aerial imagery and airborne LiDAR data, using deep learning approaches, can be applied to accurately map tree species.

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model’s classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development.

Predicting Winter Wheat Yield with Dual-Year Spectral Fusion, Bayesian Wisdom, and Cross-Environmental Validation

Winter wheat is an important grain that plays a crucial role in agricultural production and ensuring food security. Its yield directly impacts the stability and security of the global food supply. The accurate monitoring of grain yield is imperative for precise agricultural management. This study aimed to enhance winter wheat yield predictions with UAV remote sensing and investigate its predictive capability across diverse environments. In this study, RGB and multispectral (MS) data were collected on 6 May 2020 and 10 May 2022 during the grain filling stage of winter wheat. Using the Pearson correlation coefficient method, we identified 34 MS features strongly correlated with yield. Additionally, we identified 24 texture features constructed from three bands of RGB images and a plant height feature, making a total of 59 features. We used seven machine learning algorithms (Cubist, Gaussian process (GP), Gradient Boosting Machine (GBM), Generalized Linear Model (GLM), K-Nearest Neighbors algorithm (KNN), Support Vector Machine (SVM), Random Forest (RF)) and applied recursive feature elimination (RFE) to nine feature types. These included single-sensor features, fused sensor features, single-year data, and fused year data. This process yielded diverse feature combinations, leading to the creation of seven distinct yield prediction models. These individual machine learning models were then amalgamated to formulate a Bayesian Model Averaging (BMA) model. The findings revealed that the Cubist model, based on the 2020 and 2022 dataset, achieved the highest R2 at 0.715. Notably, models incorporating both RGB and MS features outperformed those relying solely on either RGB or MS features. The BMA model surpassed individual machine learning models, exhibiting the highest accuracy (R2 = 0.725, RMSE = 0.814 t·ha−1, MSE = 0.663 t·ha−1). Additionally, models were developed using one year’s data for training and another year’s data for validation. Cubist and GLM stood out among the seven individual models, delivering strong predictive performance. The BMA model, combining these models, achieved the highest R2 of 0.673. This highlights the BMA model’s ability to generalize for multi-year data prediction.

Wheat crop genotype and age prediction using machine learning with multispectral radiometer sensor data

AbstractWheat (Triticum aestivum) yield predictions can be improved by using multispectral remote sensing to identify different genotypes and crop growth stages. We propose an innovative machine learning technique aimed at classifying diverse wheat crop genotypes and providing accurate estimations of plant age. Multispectral reflectance data was obtained from different sites where various wheat genotypes were cultivated. This approach involved analyzing incoming radiation and canopy light reflectance across five distinct spectral bands using a multispectral radiometer. The newly collected remote sensing data was utilized as input for the machine learning algorithm. Impressively, the random forest model achieved an accuracy rate of 98.77% in wheat crop genotype classification. Furthermore, the proposed approach's effectiveness was confirmed through a 10‐fold cross‐validation mechanism. Moreover, a multiple linear regression model for predicting the age of wheat genotypes explained 91% of the observed variation. These findings signify significant progress in wheat crop genotype and age prediction, ultimately leading to enhanced wheat yield.

Predictive monitoring of soil organic carbon using multispectral UAV imagery: a case study on a long-term experimental field

Effective monitoring of the soil organic carbon (SOC) content at the field scale is crucial for supporting sustainable agricultural practices. This study evaluates the utility of multispectral data acquired by an unmanned aerial vehicles (UAV) during bare soil conditions for predicting the SOC content of a long-term experimental field site (LTE) in Saxony-Anhalt, Germany. Our methodology involves constructing predictive models using multiple algorithms (CUBIST, MARS, linear regression) and applying image correction techniques to enhance prediction accuracy by mitigating the influence of confounding factors such as crop residuals. Among the tested models, the CUBIST algorithm, combined with a pixel selection strategy employing a 2 m radius and stratified image correction, demonstrates the most promising results, achieving an R-squared value of 0.54 and an RMSE of 1.9 g kg−1. Spatial distribution maps generated by this optimized model effectively depict the impact of organic fertilization on the SOC content, although the clarity of these patterns varies depending on the image processing method and algorithm used. Our findings highlight the potential of utilizing UAV-derived multispectral data for SOC monitoring at the LTE scale. However, further research is warranted to assess the generalizability of this approach to agricultural fields with lower SOC variability.