The rectangular tile classification model based on Sentinel integrated images enhances grassland mapping accuracy: A case study in Ordos, China.

Arid zone grassland is a crucial component of terrestrial ecosystems and plays a significant role in ecosystem protection and soil erosion prevention. However, accurately mapping grassland spatial information in arid zones presents a great challenge. The accuracy of remote sensing grassland mapping in arid zones is affected by spectral variability caused by the highly diverse landscapes. In this study, we explored the potential of a rectangular tile classification model, constructed using the random forest algorithm and integrated images from Sentinel-1A (synthetic aperture radar imagery) and Sentinel-2 (optical imagery), to enhance the accuracy of grassland mapping in the semiarid to arid regions of Ordos, China. Monthly Sentinel-1A median value images were synthesised, and four MODIS vegetation index mean value curves (NDVI, MSAVI, NDWI and NDBI) were used to determine the optimal synthesis time window for Sentinel-2 images. Seven experimental groups, including 14 experimental schemes based on the rectangular tile classification model and the traditional global classification model, were designed. By applying the rectangular tile classification model and Sentinel-integrated images, we successfully identified and extracted grasslands. The results showed the integration of vegetation index features and texture features improved the accuracy of grassland mapping. The overall accuracy of the Sentinel-integrated images from EXP7-2 was 88.23%, which was higher than the accuracy of the single sensor Sentinel-1A (53.52%) in EXP2-2 and Sentinel-2 (86.53%) in EXP5-2. In all seven experimental groups, the rectangular tile classification model was found to improve overall accuracy (OA) by 1.20% to 13.99% compared to the traditional global classification model. This paper presents novel perspectives and guidance for improving the accuracy of remote sensing mapping for land cover classification in arid zones with highly diverse landscapes. The study presents a flexible and scalable model within the Google Earth Engine framework, which can be readily customized and implemented in various geographical locations and time periods.

Mapping burned areas in Thailand using Sentinel-2 imagery and OBIA techniques.

Monitoring burned areas in Thailand and other tropical countries during the post-harvest season is becoming increasingly important. High-resolution remote sensing data from Sentinel-2 satellites, which have a short revisit time, is ideal for accurately and efficiently mapping burned regions. However, automating the mapping of agriculture residual on a national scale is challenging due to the volume of information and level of detail involved. In this study, a Sentinel-2A Level-1C Multispectral Instrument image (MSI) from February 27, 2018 was combined with object-based image analysis (OBIA) algorithms to identify burned areas in Mae Chaem, Chom Thong, Hod, Mae Sariang, and Mae La Noi Districts in Chiang Mai, Thailand. OBIA techniques were used to classify forest, agricultural, water bodies, newly burned, and old burned regions. The segmentation scale parameter value of 50 was obtained using only the original Sentinel-2A band in red, green, blue, near infrared (NIR), and Normalized Difference Vegetation Index (NDVI). The accuracy of the produced maps was assessed using an existing burned area dataset, and the burned area identified through OBIA was found to be 85.2% accurate compared to 500 random burned points from the dataset. These results suggest that the combination of OBIA and Sentinel-2A with a 10 m spatial resolution is very effective and promising for the process of burned area mapping.

Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning.

Robust quantification of vegetative biomass using satellite imagery using one or more forms of machine learning (ML) has hitherto been hindered by the extent and quality of training data. Here, we showcase how ML predictive demonstrably improves when additional training data is used. We collated field datasets of pasture biomass obtained via destructive sampling, 'C-Dax' reflective measurements and rising plate meters (RPM) from ten livestock farms across four States in Australia. Remotely sensed data from the Sentinel-2 constellation was used to retrieve aboveground biomass using a novel machine learning paradigm hereafter termed "SPECTRA-FOR" (Spectral Pasture Estimation using Combined Techniques of Random-forest Algorithm for Features Optimisation and Retrieval). Using this framework, we show that the low temporal resolution of Sentinel-2 in high latitude regions with persistent cloud cover leads to extensive gaps between cloud-free images, hindering model performance and, thus, contemporaneous ability to forecast real-time pasture biomass. By leveraging the spectral consistency between Sentinel-2 and Planet Lab SuperDove to overcome this limitation, we used ten spectral bands of Sentinel-2, four bands of Sentinel-2 as a proxy for pre-2022 SuperDove (referred to as synthetic SuperDove or SSD), and the actual SuperDove (ASD), given that SuperDove imagery has a higher resolution and more frequent passage compared with Sentinel-2. Using their respective bands as input features to SPECRA-FOR, model performance for the ten bands of Sentinel-2 were R2 = 0.87, root mean squared error (RMSE) of 439 kg DM/ha and mean absolute error (MAE) of 255 kg DM/ha, while that for SSD increased to an R2 of 0.92, RMSE of 346 kg DM/ha and MAE = 208 kg DM/ha. The study revealed the importance of robust data mining, imagery harmonisation and model validation for accurate real-time modelling of pasture biomass with ML.

Accurate classification of land use and land cover using a boundary-specific two-level learning approach augmented with auxiliary features in Google Earth Engine.

Land use land cover (LULC) classification using remote sensing images is a valuable resource in various fields such as climate change, urban development, and land degradation monitoring. The city of Madurai in India is known for its diverse geographical elements and rich heritage, which includes the cultural sport of "Jallikattu": whose main competitor, the zebusare deeply affected by the conversion of their waterbodies and pastures into concrete jungles. Hence, monitoring land degradation is vital in preserving the geography and cultural heritage of the study area, Madurai. The "Landsat 8 Operational Land Imager tier_2 collection_2 Level_2 Surface Reflectance" image was taken for this study. The LULC classification is performed based on the following classes: forest, agriculture, urban, water bodies, uncultivated land, and bare land. The objective of the study is to incorporate auxiliary features to spectral and textural features along with a simple non-iterative clustering (SNIC) segmentation algorithm and implement a boundary-specific two-level learning approach based on support vector machines (SVM) and k nearest neighbors (kNN) classification algorithms. The overall accuracy (OA) of 95.78% and 0 .94 Kappa score (K) were obtained using a boundary-specific two-level model augmented with auxiliary feature and SNIC algorithm in comparison to PB, OB, and OBS, which achieve OA (K) of 81% (0.76), 91% (0.89), and 94.42% (0.92), respectively. The results demonstrate a notable enhancement in overall classification accuracy when augmenting the features and refining classification decisions using a boundary-specific two-level learning approach.

Long short term memory deep net performance on fused Planet-Scope and Sentinel-2 imagery for detection of agricultural crop.

In view of the challenges faced by organizations and departments concerned with agricultural capacity observations, we collected In-Situ data consisting of diverse crops (More than 11 consumable vegetation types) in our pilot region of Harichand Charsadda, Khyber Pakhtunkhwa (KP), Pakistan. Our proposed Long Short-Term Memory based Deep Neural network model was trained for land cover land use statistics generation using the acquired ground truth data, for a synergy between Planet-Scope Dove and European Space Agency's Sentinel-2. Total of 4 bands from both sentinel-2 and planet scope including Red, Green, Near-Infrared (NIR) and Normalised Difference Vegetation Index (NDVI) were used for classification purpose. Using short temporal frame of Sentinel-2 comprising 5 date images, we propose an realistic and implementable procedure for generating accurate crop statistics using remote sensing. Our self collected data-set consists of a total number of 107,899 pixels which was further split into 70% and 30% for training and testing purpose of the model respectively. The collected data is in the shape of field parcels, which has been further split for training, validation and test sets, to avoid spatial auto-correlation. To ensure the quality and accuracy 15% of the training data was left out for validation purpose, and 15% for testing. Prediction was also performed on our trained model and visual analysis of the area from the image showed significant results. Further more a comparison between Sentinel-2 time series is performed separately from the fused Planet-Scope and Sentinel-2 time-series data sets. The results achieved shows a weighted average of 93% for Sentinel-2 time series and 97% for fused Planet-Scope and Sentinel-2 time series.

A temporal-spectral value and shape change detection method integrating thematic index information and spectral band information.

Satellite imagery time series change detection methods are effective in avoiding pseudochange due to vegetation phenology to a certain extent. Traditional time series change detection methods use thematic indexes (e.g., NDVI, RVI) to obtain time series information for corresponding change detection. However, change detection methods using several thematic index time series may not make full use of other spectral band information in remotely sensed images and may still suffer from over- and under-detections. To address this challenge, a temporal-spectral value and shape change detection method integrating thematic index information and spectral band information (TISB) is proposed. Possible clouds and cloud shadowing phenomena are removed according to the changes in the spectral values of the remotely sensed images to avoid the generation of pseudochanges in clouds. The spectral and time series information is used to obtain change information from the value perspective, and then, further possible enhanced change regions from a shape perspective to obtain the final change detection results through the expectation-maximization (EM) method. Experiments with Landsat images have shown that the TISB method improves detection results by approximately 1-4% compared to the comparison method.

High-resolution soil moisture mapping using PSO-based optimized cerebellar model articulation controller (CMAC).

A good knowledge in eco-hydrological processes requires significant understanding of geospatial distribution of soil moisture (SM). However, SM monitoring remains challenging due to its large spatial variability and its dynamic time response. This study was performed to assess the performance of a particle swarm optimization (PSO)-based optimized Cerebellar Model Articulation Controller (CMAC) in generating high-resolution surface SM estimates using sentinel-2 imagery over a Mediterranean agro-ecosystem. Furthermore, the results were compared with those of PSO-based optimized group method of data handling (GMDH) as a more common data-driven method. Two different modeling approaches i.e. modeling in homogenous clusters (local approach) and modeling in entire area as an entity (global approach) were examined. Candidate predictors namely sentinel-2 spectral bands, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), digital elevation model (DEM), slope and aspect were used as the input variables to estimate SM. An intensive field survey had been done to gather in-situ SM data using a time-domain reflectometer (TDR). K-fold validation based on in-situ SM measurements demonstrated the reasonability of the SM estimation of the proposed methodology. Detecting homogeneous areas was done using genetic and particle swarm optimization algorithms. Synthesized SM product of PSO-GMDH showed a mean Normalized Root-Mean-Square Error (NRMSE) of 13.6 to 8.91 for global and local approaches in the test phase. PSO-CMAC method with an average NRMSE of 12.47 to 8.72 for global and local approaches shows the highest accuracy and outperforms the PSO-GMDH method at both local and global approaches. Overall, results revealed that clustering study area prior to running machine learning (ML) models coupled with optical satellite imagery and geophysical properties, boosts their predictive performance and can lead to more accurate mapping of SM with more heterogeneity. The results also showed that the global approach had a moderate performance in capturing the SM heterogeneity.

Remote sensing strategies to monitoring land use maps with AVHRR and MODIS data over the South Asia regions.

In South Asia, annual land use and land cover (LULC) is a severe issue in the field of earth science because it affects regional climate, global warming, and human activities. Therefore, it is vitally essential to obtain correct information on the LULC in the South Asia regions. LULC annual map covering the entire period is the primary dataset for climatological research. Although the LULC annual global map was produced from the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset in 2001, this limited the perspective of the climatological analysis. This study used AVHRR GIMMS NDVI3g data from 2001 to 2015 to randomly forests classify and produced a time series of the annual LULC map of South Asia. The MODIS land cover products (MCD12Q1) are used as data from reference for trained classifiers. The results were verified using the annual map of the LULC time series, and the space-time dynamics of the LULC map were shown in the last 15 years, from 2001 to 2015. The overall precision of our 15-year land cover map simplifies 16 classes, which is 1.23% and 86.70% significantly maximum as compared to the precision of the MODIS data map. Findings of the past 15 years show the changing detection that forest land, savanna, farmland, urban and established land, arid land, and cultivated land have increased; by contrast, woody prairie, open shrublands, permanent ice and snow, mixed forests, grasslands, evergreen broadleaf forests, permanent wetlands, and water bodies have been significantly reduced over South Asia regions.

Effect of satellite-emitted frequency sequences on Phakopsora pachyrhizi control, on soybean nutrition and yield

The obstacles in Phakopsora pachyrhizi management result especially from susceptible soybean genotypes and resistant fungal strains. The objective of the current study was to evaluate the applicability of the emission of extremely low and specific frequencies by Effatha technology in the soybean Asian rust control, nutrition, and its impact on yield. The in-vivo test followed the detached leaves method, with six treatments: frequencies 1 and 2 individually and in association; the conventional chemical treatment (fungicide azoxystrobin + benzovindiflupyr); and witnesses in presence and absence of the fungus. Frequency 1 relates to inhibition of the enzyme succinate dehydrogenase and 2 to ubiquinone oxidase. In the field, frequencies 1 and 2 associated (with the same fungicidal action of the in-vivo study); nutritional frequency; application of azoxystrobin + benzovindiflupyr + mancozeb, and control without application were evaluated. In vivo, the fungicide provided 85% control of the disease symptoms, against 65% of frequencies 1 and 2 in association, which showed a higher efficiency compared to the isolated frequencies. In the field, the rate of increase of symptoms were reduced by all treatments compared to the control. At the end of the soybean cycle, the conventional fungicide resulted in 33% severity against 56% of frequencies 1 and 2 associated, and 69.2% of the control. The emission of the frequency for increased nutrient efficiency stood out positively on yield in relation to all the other ones. The conventional application provided the highest weight of 1,000 grains, possibly a direct reflection of the better control of the disease.

Satellite imagery: a way to monitor water quality for the future?

Monitoring water at high spatial and temporal resolutions is important for maintaining water quality because the cost of pollution remediation is often higher than the cost of early prevention or intervention. In recent decades, the availability and affordability of satellite images have regularly increased, thus supporting higher-frequency and lower-cost alternative methods for monitoring water quality. The core step in satellite remote sensing detection is inverse modeling, which is used to calibrate model parameters and enhance the similarity between the model and the real system being simulated. The reflectance values measured at water quality stations are extracted from atmosphere-corrected satellite imagery for analysis. However, various external environmental, hydrological, and meteorological factors affect the evaluation results, and the results obtained with different parameters can vary. This literature review shows that nonpoint-source pollution caused by stormwater runoff can also be monitored using satellite imagery. To improve the accuracy of satellite-based water quality prediction, the temporal resolution of field measurements can be increased, thus better considering the influence of seasonality. Then, the atmospheric correction module can be improved by using available atmospheric water content products. Moreover, because water surface ripples affect reflectance, wind speed and direction should be considered when comparing water quality scenes.

Census-independent population estimation using representation learning.

Knowledge of population distribution is critical for building infrastructure, distributing resources, and monitoring the progress of sustainable development goals. Although censuses can provide this information, they are typically conducted every 10 years with some countries having forgone the process for several decades. Population can change in the intercensal period due to rapid migration, development, urbanisation, natural disasters, and conflicts. Census-independent population estimation approaches using alternative data sources, such as satellite imagery, have shown promise in providing frequent and reliable population estimates locally. Existing approaches, however, require significant human supervision, for example annotating buildings and accessing various public datasets, and therefore, are not easily reproducible. We explore recent representation learning approaches, and assess the transferability of representations to population estimation in Mozambique. Using representation learning reduces required human supervision, since features are extracted automatically, making the process of population estimation more sustainable and likely to be transferable to other regions or countries. We compare the resulting population estimates to existing population products from GRID3, Facebook (HRSL) and WorldPop. We observe that our approach matches the most accurate of these maps, and is interpretable in the sense that it recognises built-up areas to be an informative indicator of population.

Land use classification of open-pit mine based on multi-scale segmentation and random forest model.

The mining industry production is an important pillar industry in China, while its extensive production activities have led to several ecological and environmental problems. Earth observation technology using high-resolution satellite imagery can help us efficiently obtain information on surface elements, surveying and monitoring various land occupation issues arising from open-pit mining production activities. Conventional pixel-based interpretation methods for high-resolution remote sensing images are restricted by "salt and pepper" noise caused by environmental factors, making it difficult to meet increasing requirements for monitoring accuracy. With the Jingxiang phosphorus mining area in Jingmen Hubei Province as the studied area, this paper uses a multi-scale segmentation algorithm to extract large-scale main characteristic information using a layered mask method based on the hierarchical structure of the image object. The remaining characteristic elements were classified and extracted in combination with the random forest model and characteristic factors to obtain land occupation information related mining industry production, which was compared with the results of the Classification and Regression Tree model. 23 characteristic factors in three aspects were selected, including spectral, geometric and texture characteristics. The methods employed in this study achieved 86% and 0.78 respectively in overall extraction accuracy analysis and the Kappa coefficient analysis, compared to 79% and 0.68 using the conventional method.

Operational daily evapotranspiration mapping at field scale based on SSEBop model and spatiotemporal fusion of multi-source remote sensing data.

Accurate understanding of daily evapotranspiration (ET) at field scale is of great significance for agricultural water resources management. The operational simplified surface energy balance (SSEBop) model has been applied to estimate field scale ET with Landsat satellite imagery. However, there is still uncertainty in the ET time reconstruction for cloudy days based on limited clear days' Landsat ET fraction (ETf) computed by SSEBop. The Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data can provide daily surface observation over clear-sky areas. This paper presented an enhanced gap-filling scheme for the SSEBop ET model, which improved the temporal resolution of Landsat ETf through the spatio-temporal fusion with SSEBop MODIS ETf on clear days and increased the time reconstruction accuracy of field-scale ET. The results were validated with the eddy covariance (EC) measurements over cropland in northwestern China. It indicated that the improved scheme performed better than the original SSEBop Landsat approach in daily ET estimation, with higher Nash-Sutcliffe efficiency (NSE, 0.75 vs. 0.70), lower root mean square error (RMSE, 0.95 mm·d-1 vs. 1.05 mm·d-1), and percent bias (PBias, 16.5% vs. 25.0%). This fusion method reduced the proportion of deviation (13.3% vs. 25.5%) in the total errors and made the random error the main proportion, which can be reduced over time and space in regional ET estimation. It also evidently improved the underestimation of crop ET by the SSEBop Landsat scheme during irrigation before sowing and could more accurately describe the synergistic changes of soil moisture and cropland ET. The proposed MODIS and Landsat ETf fusion can significantly improve the accuracy of SSEBop in estimating field-scale ET.

A street-view-based method to detect urban growth and decline: A case study of Midtown in Detroit, Michigan, USA.

Urban growth and decline occur every year and show changes in urban areas. Although various approaches to detect urban changes have been developed, they mainly use large-scale satellite imagery and socioeconomic factors in urban areas, which provides an overview of urban changes. However, since people explore places and notice changes daily at the street level, it would be useful to develop a method to identify urban changes at the street level and demonstrate whether urban growth or decline occurs there. Thus, this study seeks to use street-level panoramic images from Google Street View to identify urban changes and to develop a new way to evaluate the growth and decline of an urban area. After collecting Google Street View images year by year, we trained and developed a deep-learning model of an object detection process using the open-source software TensorFlow. By scoring objects and changes detected on a street from year to year, a map of urban growth and decline was generated for Midtown in Detroit, Michigan, USA. By comparing socioeconomic changes and the situations of objects and changes in Midtown, the proposed method is shown to be helpful for analyzing urban growth and decline by using year-by-year street view images.

Visual saliency guided perceptual adaptive quantization based on HEVC intra-coding for planetary images.

Due to the limited storage space of spacecraft and downlink bandwidth in the data delivery during planetary exploration, an efficient way for image compression onboard is essential to reduce the volume of acquired data. Applicable for planetary images, this study proposes a perceptual adaptive quantization technique based on Convolutional Neural Network (CNN) and High Efficiency Video Coding (HEVC). This technique is used for bitrate reduction while maintaining the subjective visual quality. The proposed algorithm adaptively determines the Coding Tree Unit (CTU) level Quantization Parameter (QP) values in HEVC intra-coding using the high-level features extracted by CNN. A modified model based on the residual network is exploited to extract the saliency map for a given image automatically. Furthermore, based on the saliency map, a CTU level QP adjustment technique combining global saliency contrast and local saliency perception is exploited to realize a flexible and adaptive bit allocation. Several quantitative performance metrics that efficiently correlate with human perception are used for evaluating image quality. The experimental results reveal that the proposed algorithm achieves better visual quality along with a maximum of 7.17% reduction in the bitrate as compared to the standard HEVC coding.

Detecting landslide-dammed lakes on Sentinel-2 imagery and monitoring their spatio-temporal evolution following the Kaikoura earthquake in New Zealand.

Landslide-dammed lakes pose a risk for upriver and downriver communities and infrastructure. The 2016 Kaikoura earthquake affected the northeastern region of the South Island in New Zealand, triggering numerous landslides that dammed river courses leading to the formation of hundreds of dammed lakes. Detecting and monitoring landslide-dammed lakes is important for disaster management. Satellite remote sensing imagery is often complementary to field acquisitions to obtain an overview of large and remote areas and thus can be exploited to monitor landslide-dammed lakes. Yet, the strengths and limitations of freely available multi-temporal satellite imagery for landslide-dammed lake assessment remain largely unexplored. This study aimed at automatically mapping landslide-dammed lakes caused by the 2016 Kaikoura earthquake and monitoring their evolution using time series of Sentinel-2 imagery and the computing capabilities of the Google Earth Engine. Our approach combined dynamic thresholding, change detection, and connected component analysis. Landslide-dammed lakes larger than 300 m2 and located on relatively flat terrain were detected with reasonable accuracy, while lakes located in steeply incised valleys were detected less frequently. Despite the challenging topographical and environmental characteristics of the study area, we were able to detect landslide-dammed lake candidates at a regional scale. Temporal monitoring of the evolution of the landslide-dammed lake area revealed four distinct patterns: 1) constant, 2) increasing, 3) decreasing, and 4) variable. Our approach contributes to the understanding of the utility and limitations of temporal and spatial monitoring of landslide-dammed lakes, their potential cascading hazards and their interactions.

Automated satellite remote sensing of giant kelp at the Falkland Islands (Islas Malvinas).

Giant kelp populations that support productive and diverse coastal ecosystems at temperate and subpolar latitudes of both hemispheres are vulnerable to changing climate conditions as well as direct human impacts. Observations of giant kelp forests are spatially and temporally uneven, with disproportionate coverage in the northern hemisphere, despite the size and comparable density of southern hemisphere kelp forests. Satellite imagery enables the mapping of existing and historical giant kelp populations in understudied regions, but automating the detection of giant kelp using satellite imagery requires approaches that are robust to the optical complexity of the shallow, nearshore environment. We present and compare two approaches for automating the detection of giant kelp in satellite datasets: one based on crowd sourcing of satellite imagery classifications and another based on a decision tree paired with a spectral unmixing algorithm (automated using Google Earth Engine). Both approaches are applied to satellite imagery (Landsat) of the Falkland Islands or Islas Malvinas (FLK), an archipelago in the southern Atlantic Ocean that supports expansive giant kelp ecosystems. The performance of each method is evaluated by comparing the automated classifications with a subset of expert-annotated imagery (8 images spanning the majority of our continuous timeseries, cumulatively covering over 2,700 km of coastline, and including all relevant sensors). Using the remote sensing approaches evaluated herein, we present the first continuous timeseries of giant kelp observations in the FLK region using Landsat imagery spanning over three decades. We do not detect evidence of long-term change in the FLK region, although we observe a recent decline in total canopy area from 2017-2021. Using a nitrate model based on nearby ocean state measurements obtained from ships and incorporating satellite sea surface temperature products, we find that the area of giant kelp forests in the FLK region is positively correlated with the nitrate content observed during the prior year. Our results indicate that giant kelp classifications using citizen science are approximately consistent with classifications based on a state-of-the-art automated spectral approach. Despite differences in accuracy and sensitivity, both approaches find high interannual variability that impedes the detection of potential long-term changes in giant kelp canopy area, although recent canopy area declines are notable and should continue to be monitored carefully.

A Semi-Supervised Deep Rule-Based Approach for Complex Satellite Sensor Image Analysis.

Large-scale (large-area), fine spatial resolution satellite sensor images are valuable data sources for Earth observation while not yet fully exploited by research communities for practical applications. Often, such images exhibit highly complex geometrical structures and spatial patterns, and distinctive characteristics of multiple land-use categories may appear at the same region. Autonomous information extraction from these images is essential in the field of pattern recognition within remote sensing, but this task is extremely challenging due to the spectral and spatial complexity captured in satellite sensor imagery. In this research, a semi-supervised deep rule-based approach for satellite sensor image analysis (SeRBIA) is proposed, where large-scale satellite sensor images are analysed autonomously and classified into detailed land-use categories. Using an ensemble feature descriptor derived from pre-trained AlexNet and VGG-VD-16 models, SeRBIA is capable of learning continuously from both labelled and unlabelled images through self-adaptation without human involvement or intervention. Extensive numerical experiments were conducted on both benchmark datasets and real-world satellite sensor images to comprehensively test the validity and effectiveness of the proposed method. The novel information mining technique developed here can be applied to analyse large-scale satellite sensor images with high accuracy and interpretability, across a wide range of real-world applications.

Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image.

This exploration primarily aims to jointly apply the local FCN (fully convolution neural network) and YOLO-v5 (You Only Look Once-v5) to the detection of small targets in remote sensing images. Firstly, the application effects of R-CNN (Region-Convolutional Neural Network), FRCN (Fast Region-Convolutional Neural Network), and R-FCN (Region-Based-Fully Convolutional Network) in image feature extraction are analyzed after introducing the relevant region proposal network. Secondly, YOLO-v5 algorithm is established on the basis of YOLO algorithm. Besides, the multi-scale anchor mechanism of Faster R-CNN is utilized to improve the detection ability of YOLO-v5 algorithm for small targets in the image in the process of image detection, and realize the high adaptability of YOLO-v5 algorithm to different sizes of images. Finally, the proposed detection method YOLO-v5 algorithm + R-FCN is compared with other algorithms in NWPU VHR-10 data set and Vaihingen data set. The experimental results show that the YOLO-v5 + R-FCN detection method has the optimal detection ability among many algorithms, especially for small targets in remote sensing images such as tennis courts, vehicles, and storage tanks. Moreover, the YOLO-v5 + R-FCN detection method can achieve high recall rates for different types of small targets. Furthermore, due to the deeper network architecture, the YOL v5 + R-FCN detection method has a stronger ability to extract the characteristics of image targets in the detection of remote sensing images. Meanwhile, it can achieve more accurate feature recognition and detection performance for the densely arranged target images in remote sensing images. This research can provide reference for the application of remote sensing technology in China, and promote the application of satellites for target detection tasks in related fields.