Image Time Series Analysis Research Articles

Bayesian Inference for Post-Processing of Remote-Sensing Image Classification

A key component of remote-sensing image analysis is image classification, which aims to categorize images into different classes using machine-learning methods. In many applications, machine-learning classifiers assign class probabilities to each pixel. These class probabilities serve as input for post-processing techniques that aim to improve the results of machine-learning algorithms. This paper proposes a new post-processing algorithm based on an empirical Bayes approach. We employ non-isotropic neighborhood definitions to capture the impact of borders between land classes in the statistical model. By incorporating expert knowledge, the algorithm improves the consistency of the classified map. This technique has proven its efficacy for large-scale data processing using image time-series analysis. The proposed method is a key component of a time-first, space-based approach for big Earth-observation data processing. It is available as open source as part of the R package sits.

Mechanically and accurately calculate river width in vegetation areas by coupling Sentinel-1 and -2 imageries within land-water-mixed pixels

Accurately measuring river width has been one of greatest challenges due to the presence of mixed land–water pixels intersecting river boundaries. Therefore, this study proposed a novel mechanical method (RW-vebasud), instead of traditionally empirical models, to estimate river width within a pixel in vegetation areas based on time series analysis of Sentinel-1 and Sentinel-2 spaceborne multispectral images. We initially explored the mechanism of variation in backscatter intensity (σ) with enhanced vegetation index (EVI) whereby we successfully removed noises in σ–EVI relationship resulted from vegetation growth. Then, for the first time a smooth functional relationship between water area proportion and backscatter intensity within a ROI (or region of interest) was constructed. Consequently, subpixel water–land separation based on the mechanism process was realized. The novel method could not only work at large-scaled rivers (satellite-visible) but perform well at small-scaled rivers within a water-land mixed pixel (satellite-invisible). A total of 197 measurements for river widths in China during 2016 ∼ 2021 were used for model verification, demonstrating a positive correlation between EVI and σ, with R2 ranging from 0.16 to 0.69 (P<0.05). The RW-vebasud exhibited superior accuracy in calculating river width compared to the widely used MNDWI (modified normalized difference water index). The Root Mean Square Error (RMSE) decreased by 4.32 ∼ 6.65 m when the river width was less than 90 m and by 66.12 % when it exceeded 90 m, compared to MNDWI. Remarkably, RW-vebasud maintains satisfactorily high accuracy (the Nash-Sutcliffe efficiency coefficient: NSE=0.70 and RMSE=3.19) even at the spatial scale less than 3 times the image resolution, breaking the internationally accepted limit that river width extraction can only be accurate when the river width is greater than 3 times the satellite resolution. Moreover, the accuracy of this method is better than that with the currently well-known global river width datasets GRWL and MERIT Hydro. For the RW-Vebasud/GRWL/MERIT Hydro datasets, the NSE=0.99 /0.93/0.87, the RMSE=5.99/42.33/54.27, and the R2 = 0.99/0.91/0.74, respectively. The application of RW-vebasud in China shows that river widths in wet and dry seasons exhibited an increasing trend over the previous six years (2016–2021), as global warming accelerated glacier melting and increased rainfall quantity, with an average growth rate of 2.26 m/year (wet, P<0.05) and 2.17 m/year (dry, P<0.05), respectively. In response to the summer/winter Asian monsoons, most rivers widen in summer. The largest river width occurs in the Yellow River Basin (YLRB, 155.28 m on average), while the smallest occurs in the Hai River Basin (HARB, 22.99 m on average). The method proposed in this study can provide efficient techniques for surface river-width reconstruction which can greatly facilitate global resource and environmental modelling.

Time series analysis of L-band PALSAR-2 images in Istanbul and Kocaeli, Turkey

ABSTRACT Conducting long measurements of infrastructure deformation is a critical engineering task. Conventional methods are both time-consuming and expensive, limiting their use for large-scale applications. The synergy of synthetic aperture radar (SAR) and geographic information systems (GIS) offers a complementary approach. This study focuses on the feasibility of using time series analysis of L-band PALSAR-2 images to discover land displacements in Istanbul and Kocaeli, significant industrial and residential areas in Turkey. PALSAR-2 phase and intensity information were analyzed. For phase analysis, 14 L-band images from 2014 to 2021 were taken into account. Small baseline subset (SBAS) analysis was performed using 44 pairs, and results of the velocity, coherence and backscattering values are presented. Coherence of all pairs and their correlations were calculated. Principal Component Analysis (PCA) reduced the dimension of coherence pairs, enhancing feature extraction and the final geocoded velocity map revealed a fastest subsidence rate of −58 mm/yr and a mean subsidence of −20 mm/yr. These findings were confirmed through mean vertical velocity from Sentinel-1 datasets and field observations. The results showed that immature land subsidence in the mentioned areas are growing slowly, which can be taken as a serious risk in future.

Tomato Production Prediction Based on Deep Learning Algorithm-Cascade-PSPNET and Bayes

Accounting the problem of small sample size in tomato yield statistics, a dual-fusion prediction analysis model based on Bayes theory and deep learning algorithm Cascade-PSPNET is proposed. The tomato yield prediction is conducted based on remote sensing image time series analysis and multi-source information fusion theory with Bayesian theory and credibility weighting. First, the area of tomato planting is analyzed through semantic segmentation algorithms of remote sensing images during the tomato planting process. The yield is predicted by variables such as planting area fluctuation, disaster cycle fluctuation, etc. Through analyzing the reduced yield affected by disasters in different time periods of remote sensing images during planting process, the value chain of tomato industry is calculated by comprehensively analyzing price-value system, inflation coefficient, and unit area yield. At the same time, the annual patent application volume is used to predict the change of tomato yield year by year according to Bayesian theory, and the relationship between annual patent application volume and tomato yield year by year under different confidence levels is analyzed. The results show that it is feasible to use the Bayes method with semantic segmentation algorithms of remote sensing images to predict tomato yield. Next, the experiment of fusion prediction between two prediction models in the same target area will be carried out for verification.

Analysis and forecasting of shoreline changes in Amurang Bay

Amurang Bay has a very high development potential with the characteristics of a sloping and shallow topography and one of the areas as the capital of the South Minahasa district which is vulnerable to changes in the coastline. This analysis is used in order to analyse the changes that occur to the coastline in Kawangkoan Bawah and to see the changes over the next 10 years. Changes in the coastline can be monitored using remote sensing satellite technology, in a multi-temporal method as the comparative method or time series image analysis (last 5 years). The data analysis technique was carried out through ArGIS software using an additional tool, named DSAS. results of analysis of shoreline changes using NSM and LRR calculations in 2017-2022. Overall, the indications are that abrasion and accretion always occur every year so that they can change the shape of the beach over the last 5 years. The speed of movement of the coastline -5.9m/year. As for the speed of retreat of the coastline is -0.37m/year. The results of observation and analysis show that the coastline of Kawangkoan Bawah Village in Teluk Amurang is basically dynamic because it is found that abrasion and accretion occur every year. Recommended further studies related to land use patterns, sea level rise, and morphological changes to the existence and sustainability of the coast. We also recommend conducting in-depth studies that rely on field measurements to include the effect of momentary water levels in shoreline position monitoring

Design of a Multilayer Perceptron Network Based on the Normalized Histogram to Develop Yields Predictive Model

This article presents a multilayer perceptron (MLP) for patio-temporal remote sensing analysis of satellite image time series for a yield prediction model. This paper illustrates the model for crop yield prediction from the spatial cumulation of normalized difference vegetation index (NDVI) image time series at the province level. The methodological framework comprises the transformation of each NDVI image into a histogram to ensure no loss of information in the mapping of high- dimensional/unstructured NDVI images into pixels consideration, to be then used in training the MLP. The research work also includes an analysis of several activation functions for the hidden layer and testing their consequences on accuracy, including Radial-Basis (RadBas), Logarithmic-Sigmoid (LogSig), Hyperbolic-Tangent Sigmoid (TanSig), which depend mainly on exponential functions and limit the amplitude of the output. The proposed approach was utilized to predict the winter crop yield in Diwaniyah-Iraq province, one of the main agriculture regions, whose economy considerably depends on crop production. It can also be extended to other crops and other regions in Iraq. The proposed methodology showed the ability to predict the crop yield around seven-nine weeks before harvest. It also, outperformed the performance of traditional approaches by transforming the input into a more convenient form that reflects more useful information. The results show that the proposed model provides efficient accuracy (determination coefficient R2 &gt; 0.85 and error level &lt;0.24).

Image Segmentation of the Sudd Wetlands in South Sudan for Environmental Analytics by GRASS GIS Scripts

This paper presents the object detection algorithms GRASS GIS applied for Landsat 8-9 OLI/TIRS data. The study area includes the Sudd wetlands located in South Sudan. This study describes a programming method for the automated processing of satellite images for environmental analytics, applying the scripting algorithms of GRASS GIS. This study documents how the land cover changed and developed over time in South Sudan with varying climate and environmental settings, indicating the variations in landscape patterns. A set of modules was used to process satellite images by scripting language. It streamlines the geospatial processing tasks. The functionality of the modules of GRASS GIS to image processing is called within scripts as subprocesses which automate operations. The cutting-edge tools of GRASS GIS present a cost-effective solution to remote sensing data modelling and analysis. This is based on the discrimination of the spectral reflectance of pixels on the raster scenes. Scripting algorithms of remote sensing data processing based on the GRASS GIS syntax are run from the terminal, enabling to pass commands to the module. This ensures the automation and high speed of image processing. The algorithm challenge is that landscape patterns differ substantially, and there are nonlinear dynamics in land cover types due to environmental factors and climate effects. Time series analysis of several multispectral images demonstrated changes in land cover types over the study area of the Sudd, South Sudan affected by environmental degradation of landscapes. The map is generated for each Landsat image from 2015 to 2023 using 481 maximum-likelihood discriminant analysis approaches of classification. The methodology includes image segmentation by ‘i.segment’ module, image clustering and classification by ‘i.cluster’ and ‘i.maxlike’ modules, accuracy assessment by ‘r.kappa’ module, and computing NDVI and cartographic mapping implemented using GRASS GIS. The benefits of object detection techniques for image analysis are demonstrated with the reported effects of various threshold levels of segmentation. The segmentation was performed 371 times with 90% of the threshold and minsize = 5; the process was converged in 37 to 41 iterations. The following segments are defined for images: 4515 for 2015, 4813 for 2016, 4114 for 2017, 5090 for 2018, 6021 for 2019, 3187 for 2020, 2445 for 2022, and 5181 for 2023. The percent convergence is 98% for the processed images. Detecting variations in land cover patterns is possible using spaceborne datasets and advanced applications of scripting algorithms. The implications of cartographic approach for environmental landscape analysis are discussed. The algorithm for image processing is based on a set of GRASS GIS wrapper functions for automated image classification.

Fractional Calculus in Signal Processing: The Use of Fractional Calculus in Signal Processing Applications, Such as Image Denoising, Filtering, and Time Series Analysis

Fractional calculus has transformed signal processing by providing a more flexible representation of complex signals. This article explores its applications in image denoising, filtering, and time series analysis, highlighting its potential to revolutionize signal processing methodologies. Fractional calculus, dealing with derivatives and integrals of non-integer orders, captures long-memory and self-similar properties in real-world signals. Image denoising benefits from fractional derivatives and integrals, preserving essential details while removing noise. Filtering signals with fractional calculus allows for dynamic adaptability to changing signal characteristics. Time series analysis benefits from more accurate modelling, enhancing predictive capabilities. The future scope of fractional calculus in signal processing promises further advancements, making it a valuable tool for researchers and practitioners seeking to analyze complex signals across various domains.

Monitoring of large-scale forest restoration: Evidence of vegetation recovery and reversing chronic ecosystem degradation in the mountain region of Pakistan

Global ecosystem restoration efforts are aimed at climate change mitigation. In response to the challenge of global warming and supporting local adaptation, the Billion Tree Tsunami Afforestation Program (BTAP) was launched in 2014 to restore depleted forest ecosystems by extensive afforestation and/or reforestation in the Khyber Pakhtunkhwa Province of Pakistan. Under the BTAP, afforestation of all categories was carried out in an area of 300,000 ha, and 160 million plants were distributed under Farm Forestry and 4509 enclosures were established for Assisting Natural Regeneration (ANR) with the help of the local community. The present study evaluated historic deforestation trends using bi-temporal (1990–2010) change analysis and the performance of recent forest ecosystem restoration efforts based on time series analysis of stallite images. A total of 226 afforestation sites of the BTAP – Phase I were examined to determine the vegetation growth and evidence of ecosystem restoration efforts by regression and trend analysis of the annual normalized difference vegetation index (NDVI) composites from 2014 to 2021. The forest plantation and protected natural regeneration performance across the three key forest management regions of the Southern, Malakand and Northern zones remained variable, with growth values of 29%, 47% and 24%, respectively. The results suggest that the three forest regions lost 3.2% of the forest between 1990 and 2010. While accounting for most conservative figures validated from satellite data, the BTAP interventions during 2014–2018 improved the overall forest cover from 14.5% to 16.5% in these regions. The framework developed in this study and the derived results can help to formulate an evidence-based assessment of indicators for ecological restoration and nature-based solutions.

Brain perfusion imaging by multi-delay arterial spin labeling: Impact of modeling dispersion and interaction with denoising strategies and pathology.

Arterial spin labeling (ASL) acquisitions at multiple post-labeling delays may provide more accurate quantification of cerebral blood flow (CBF), by fitting appropriate kinetic models and simultaneously estimating relevant parameters such as the arterial transit time (ATT) and arterial cerebral blood volume (aCBV). We evaluate the effects of denoising strategies on model fitting and parameter estimation when accounting for the dispersion of the label bolus through the vasculature in cerebrovascular disease. We analyzed multi-delay ASL data from 17 cerebral small vessel disease patients (50 ± 9 y) and 13 healthy controls (52 ± 8 y), by fitting an extended kinetic model with or without bolus dispersion. We considered two denoising strategies: removal of structured noise sources by independent component analysis (ICA) of the control-label image timeseries; and averaging the repetitions of the control-label images prior to model fitting. Modeling bolus dispersion improved estimation precision and impacted parameter values, but these effects strongly depended on whether repetitions were averaged before model fitting. In general, repetition averaging improved model fitting but adversely affected parameter values, particularly CBF and aCBV near arterial locations in patients. This suggests that using all repetitions allows better noise estimation at the earlier delays. In contrast, ICA denoising improved model fitting and estimation precision while leaving parameter values unaffected. Our results support the use of ICA denoising to improve model fitting to multi-delay ASL and suggest that using all control-label repetitions improves the estimation of macrovascular signal contributions and hence perfusion quantification near arterial locations. This is important when modeling flow dispersion in cerebrovascular pathology.

Search and assessment of urban heat islands on digital satellite images

Formulation of the problem. The development of urbanization processes resulted in Urban Heat Islands (UHI) - ur-ban areas of high temperatures due to the dominance of artificial surfaces that absorb and retain heat. UHIs adversely affect the environmen-tal conditions of cities and people's health. Satellite images in the thermal infrared range of the electromagnetic spectrum allow identifying areas of the high thermal back-ground of urbanized territories for management decisions support aimed at improving urban landscapes. The aim of the work is to develop a methodology for temperature anomalies analy-sis and urban heat islands detection on digital space images from Landsat 8 satellite in the thermal infrared range of the electromagnetic spectrum. Methodology of UHI detection. The methodology proposed in the paper includes a sequence of stages of collecting, and preprocessing satellite data, generating land sur-face temperature maps, identifying temperature anomalies, comprehensive analysis of high-temperature zones based on different-time data, and identifying areas of high temperatures stable over time. Land Surface Temperature estimation. Land Surface Temperature (LST) is esti-mated from the band 10 data of space images from the Landsat 8 satellite. The initial data are subjected to atmospheric correction, after which the spectral radiation in the band is converted to brightness temperature, and then to LST (Celsius degrees). UHI mapping. On each survey date, UHIs are identified as temperature anomalies - LST map pixels with values higher than the LST mean plus standard deviation within the study area. Time series analysis of satellite images. UHI mapping is based on a time series of Landsat 8 images acquired during the warm season (when ambient temperatures are above zero) to eliminate the effect of snow and ice on the observation results. According to the time series of LST maps of different years, stable temperature anomalies are dis-tinguished - UHIs presented on all images of the time series. Conclusions. Time-stable UHIs of the urbanized territory are mapped and ana-lyzed using Landsat 8 LST data time series. The areas of the high thermal background are compared with the classes of the earth's surface. It is concluded that increasing ur-ban density contributes to the accumulation of heat and increases the ambient tem-perature. The maps of LST distribution, vegetation indices, and UHI generated in the work can be used in urban planning tasks together with traditional sources of spatial information to obtain new information on improving the city's resistance to heat waves. UHI observation data are necessary for zoning areas with different land use types, for example, increasing the amount of open space and greenery, and improving the thermal comfort of citizens.

Coseismic and post-seismic characteristics of the 2021 Ganaveh earthquake along the Zagros foredeep fault based on InSAR data

SUMMARY The Ganaveh earthquake on 2021 April 18 (Mw 5.8) occurred in the southwest of the Dezful embayment of the Zagros Mountain belt, Iran, as a mainly compressive event. The InSAR coseismic displacement maps reveal a maximum of 17 cm of surface displacement in the satellite line of sight direction. InSAR inversion indicates a low-angle NE-dipping causative fault plane with a maximum slip of 95 cm at ∼6 km depth. It highlights the occurrence of the Ganaveh earthquake within the competent layers of the Zagros sedimentary cover, beneath the Gachsaran formation. A slight sinistral slip component (2.9 cm) is retrieved which is compatible with the USGS focal mechanism. Time-series analysis of SAR images after the main shock until the end of 2021 indicates a maximum of 7 cm of post-seismic surface displacement with a similar strike and pattern as the coseismic phase. This similarity and the distribution of aftershocks suggest an afterslip mechanism for the post-seismic phase. The inversion of post-seismic cumulative displacement evaluates a maximum of 30 cm slip at a depth of ∼5 km along the coseismic causative fault. A regional compressional stress regime (N041°E for the direction of the σ1 stress axis) is constrained by using the focal mechanisms of 39 earthquakes occurring between 1968 and 2021, including the Ganaveh main shock and its five larger aftershocks. Applying this direction of compression on the Ganaveh fault plane also results in a minor sinistral movement, consistent with the geodetic results. The relocated main shock and aftershocks as well as our InSAR coseismic displacement situations on the hanging wall of the Zagros Foredeep fault highlight it as the causative fault of the Ganaveh earthquake. To fit the geometry of the Ganaveh rupture plane with the Zagros Foredeep fault, we modelled a listric fault plane and its slip distribution using the available geological data. The retrieved slip variation on the listric plane is in close agreement with the slip pattern on the modelled planar geometry. The low dip angle of the rupture plane combined with a listric geometry highlights the thin-skin characteristics of the Zagros Foredeep fault as the causative fault of the Ganaveh earthquake. The occurrence of this moderate magnitude earthquake on the Zagros Foredeep fault underlines its role as the western structural boundary for the recurrence of Mb &amp;gt; 5 events in the Dezful embayment.

Monitoring Technology Around Trains Using AI and Image Processing

In recent years, the development of AI technology has led to rapid improvements in various fields, such as image recognition, language processing, and time series analysis. In the automotive field, driver assistance systems using cameras and sensors have already been put to practical use, and research on automatic driving is also active. On the other hand, some operators have just started to conduct tests of forward monitoring using cameras and sensors in railway. In this paper, we introduce our proposed research on AI application and anomaly detection using cameras and sensors in trains to improve train safety.

Efficiency of SPIRITS (Software for Processing and Interpretation of Remotely Sensed Image Time Serie) to Ecological Modeling: New Functionalities and Use Examples

We studied the effectiveness of SPIRITS processing software used to monitor drought. In this article, we propose practice steps and we prove that ecological modeling can be available with remote sensing data on a larger scale (for any place in the world) with SPIRITS. The studies summarize some important analyses of remote sensing time series at high temporal and medium spatial resolution. The Software for the Processing and Interpretation of Remotely sensed Image Time Series (SPIRITS) is a stand-alone flexible analysis environment created to facilitate the processing and analysis of large image time series and ultimately for providing clear information about vegetation status in various graphical formats to ecological modeling. The examples of operational analyses are taken from several recent drought monitoring articles. We conclude with considerations on SPIRITS use also in view of data processing requirements imposed by the coming generation of remote sensing products at high spatial and temporal resolution, such as those provided by the Sentinel sensors of the European Copernicus program.

Detecting dyeing machine entanglement anomalies by using time series image analysis and deep learning techniques for dyeing-finishing process

Tangle anomalies represent a critical quality bottleneck in the dyeing and finishing process. The key problem is that most dyeing and finishing factories in Taiwan are small and medium-sized enterprises. The operating dyeing machines can only detect entanglement through the shutdown alarm or experienced craftsmen. In this study, machine data of operating dyeing machines are collected. The time-series data image technology of the Gramian Angular Summation Field, Gramian Angular Difference Field, and Markov Transition Field is combined with a convolutional neural network to develop an entanglement detection model. Industry manufacturers cooperating with universities collected 1,750,977 pieces of production data from 1,848 batches for verification and study. The results show that the optimal detection time for entanglement detection is 220 s, using the MTF conversion method with a moving window of 20, a parameter learning rate of 0.00005, and a batch size of 200. The results are systematically introduced into the field. It has been verified that when signs of entanglement occur, an alarm can be sent to the relevant personnel to solve the problem in the shortest time. As a result, manufacturers can greatly reduce the cost of quality loss and scheduling bottlenecks caused by downtime caused by entanglement.

Geometric accuracy assessment and a framework for automatic sub-pixel registration of WFI images from CBERS-4, CBERS-4A, and Amazonia-1 satellites over Brazil

Brazil faces the challenge of conciliating food production with natural vegetation preservation, and the government has been investing in Earth Observation satellites to assist in this task. In this context, images from the Wide-Field Imager (WFI) sensor onboard the China-Brazil Earth Resources Satellite (CBERS-4), CBERS-4A, and Amazonia-1 have been used in remote sensing applications in Brazil. However, the geometric accuracy of the WFI data has not yet been documented in the literature, as it was done for other satellites/sensors such as TERRA/MODIS, Landsat-8/OLI, and Sentinel-2/MSI. This work presents the first study to assess the geometric accuracy of WFI images along different spectral channels, from multi-temporal images, and taking Sentinel-2/MSI images as a reference. Surface reflectance WFI images, Level-4 (orthorectified) with spatial resolution of 55 m (CBERS-4A) and 64 m (CBERS-4 and Amazonia-1) were analysed. Thousands of control points (CPs) were used to quantify the geometric accuracy of more than 300 WFI images and to construct multiple mapping functions to correct the displacements found. The NIR band was taken as a reference in the inter-channel (band-to-band) registration evaluation. In this case, all tiles had an RMSE average of fewer than 0.44 pixels. For the multi-temporal case, the CBERS-4A/WFI had the highest average RMSE (0.87 ± 0.34 pixels). Considering the Sentinel-2/MSI as a reference, there were observed shifts up to 1.45 pixels for CBERS-4/WFI and Amazonia-1/WFI and 2.5 pixels for CBERS-4A/WFI. Given the displacements found, image registration is needed for further time series analysis of WFI images for several applications that requiring precise sub-pixel registration (i.e., land use cover change). As a result, we propose a framework for the automatic registration of WFI images to properly foster the use of WFI images. This framework substantially reduced the misregistrations, decreasing the RMSE average to less than 0.29 pixels for the WFI images from the three satellites. The use of the 2nd degree polynomial as a mapping function proved to be appropriate for registering the WFI data.

Time-series analysis of Sentinel-2 satellite images for sunflower yield estimation

Accurate estimates and predictions of sunflower crop yields at the pixel and field level are critically important for farmers, service dealers, and policymakers. Several models based on remote sensing data have been developed in yield assessment, but their robustness—especially in small field scale areas—needs to be examined. Here we aim to develop a robust methodology for estimation/prediction of sunflower yield at pilot field scale using Sentinel-2 remote sensing satellite imagery. We conducted the study in Mezőhegyes, south-eastern Hungary. The Random Forest Regression (RFR), a machine learning technique was used in this research to translate the Sentinel-2 spectral bands to sunflower yield based on crop yield data provided by a combine harvester equipped with a yield-monitoring system. Sentinel-2 images obtained from April to September were used to find the best image for prediction. The satellite image acquired on June 28 was found best and considered further for prediction sunflower yield. A developed training model was tested and validated in 10 different parcels to evaluate the performance of the prediction. We examined the results of the prediction model (predicted) against the actual yield data (observed) collected by a combine harvester. The results demonstrated that using 10 spectral bands from Sentinel-2 imagery the best time to predict sunflower yields was between 85 and 105 d into the growing season during the flowering stage. This model achieved high accuracy with low normalized root means square error (RMSE) ranging from 121.9 to 284.5 kg/ha for different test fields. Our results are promising because they prove the possibility of predicting sunflower grain yield at the pixel or field level, 3–4 months before the harvest, which is crucial for planning food policy.

An interactive time series image analysis software for dendritic spines

Live fluorescence imaging has demonstrated the dynamic nature of dendritic spines, with changes in shape occurring both during development and in response to activity. The structure of a dendritic spine correlates with its functional efficacy. Learning and memory studies have shown that a great deal of the information stored by a neuron is contained in the synapses. High precision tracking of synaptic structures can give hints about the dynamic nature of memory and help us understand how memories evolve both in biological and artificial neural networks. Experiments that aim to investigate the dynamics behind the structural changes of dendritic spines require the collection and analysis of large time-series datasets. In this paper, we present an open-source software called SpineS for automatic longitudinal structural analysis of dendritic spines with additional features for manual intervention to ensure optimal analysis. We have tested the algorithm on in-vitro, in-vivo, and simulated datasets to demonstrate its performance in a wide range of possible experimental scenarios.

Sugarcane crop classification using time series analysis of optical and SAR sentinel images: a deep learning approach

ABSTRACT Remote Sensing-based multi-time point imagery helps incorporate the potentiality of time series analysis in crop classification studies. Single timepoint imagery has limitations in this aspect due to a comparatively similar spectral signature of crops. Even in multi-time point imagery, the viability of optical datasets is thwarted by clouds in crop growing seasons. Hence, researchers have used the all-weather imaging capabilities of Synthetic Aperture Radar (SAR) for crop classification. This all-weather capability of SAR and the multispectral capability of Optical datasets combined with their time series data hold great potential in remote sensing-based crop classification. Nevertheless, the underlying patterns of the combined SAR and optical time series haven’t been meticulously explored, especially for socio-economically important crops like sugarcane. Therefore, this study proposes using the Sentinel-1 and Sentinel-2 time-series datasets and crop phenology information to develop a Neural Network capable of identifying sugarcane crops in the sugar belts of Western-Uttar Pradesh. Studies are done for the year 2020 using a Long short-term memory (LSTM) neural network obtaining high accuracies in classifying sugarcane and non-sugarcane classes using optical and SAR time-series analysis datasets. The synthetic dataset has also been developed to enhance the convergence of the deep learning model, producing higher accuracy than utilizing the original dataset. Consequently, the study contributes to remote sensing-based crop classification and sets a foundation for further advancements in this domain.

Monitoring of Coastal Aquaculture Sites in the Philippines through Automated Time Series Analysis of Sentinel-1 SAR Images

With the unprecedented expansion of aquaculture around the world, there is a critical need to monitor its progress. In Palawan, Philippines, coastal aquaculture is gaining momentum towards increasing fish production, a pressure that presents a challenge to the sustainability of these areas. In this paper, we explore the application of Earth observation methods to map coastal aquaculture development in Palawan and evaluate the extent of its change. The European Space Agency Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral instrument sensor data were applied in fully automatic mode to build maps of Palawan coastal aquaculture. The maps were validated using Google Earth high-resolution optical images and in situ observations in Malampaya Sound, and demonstrated a successful detection rate of 72%, while the false alarm rate was less than 7.5%. Objects only 5 m across, four times smaller than the spatial resolution of the Sentinel-1 sensors, were successfully detected using the developed methodology, thus exceeding the capabilities of other published methods that are limited to detecting large groups of aquaculture structures. The maps revealed aquaculture structures in high quantities in Malampaya Sound, Taytay Bay, and other locations in the coastal waters of Palawan, Philippines. A significant change of aquaculture spatial distribution was identified by comparing aquaculture maps generated with an interval of three years. This new automated methodology was validated as robust for mapping aquaculture objects in Palawan, Philippines, and can be applied to aquaculture studies in other regions worldwide.