Medium Resolution

Hello -  I am curious to know whether there are any future plans to image coastal Antarctica regions with SuperDove satellites this coming austral summer season when the sun elevation is above 10 degrees and other collection criteria are satisfactory and within latitudinal range of the satellites. I noticed in the Planet Explorer application that SuperDove imagery exists from 2024 and earlier within the latitude range of 75 degrees to 77 degrees south. It appears that no further imagery has been acquired in the 2025 and 2026 time periods. Thank you for any insight you are able to provide! 

Hi everyone,I'm already a Planet Exploration subscriber, and I'm hoping someone here can point me in the right direction.My family and I are trying to resolve a land boundary dispute, and we only need one historical PlanetScope image of a very small location.After subscribing, I realized that the imagery we need appears to require one of the much more expensive plans (around $450+), which we honestly didn't expect. We thought the Exploration subscription would be enough, but unfortunately we misunderstood the differences between the plans.We're not looking for continuous monitoring or large datasets—just one image from a specific period that could help settle this issue.The location is:36°07'27.3"N 36°30'31.0"EThe ideal image would be taken between May 30, 2019 and May 30, 2020. During that period, the trees had already been cleared, but the concrete boundary marker was still in place before it was later removed.If anyone has access to this imagery, or knows of a more affordable way to

In our recent paper, river water depths up to 20 m are inferred from SuperDove imagery and the results are compared with those from Landsat-9 imagery! Vey promising results from the 8-band SuperDove CubeSats! Check out our open access paper here:https://ieeexplore.ieee.org/abstract/document/9810335

Hi everyone,I am currently working with PlanetScope Visual Basemaps, which are licensed under an educational license. According to the product data and specifications, the positioning accuracy is approximately 4.77 meters in high mountainous areas (Kuala Lumpur, Malaysia). The Observation: In my area of interest (hilly terrain), I have observed a distinct color artifact along the boundaries of landslides (the interface between bare soil and vegetation). One edge of the feature consistently shows a Red fringe. The opposite edge shows a Green/Cyan fringe. I am trying to determine if this is an inherent characteristic of the data in steep terrain or something that requires specific post-processing. My Questions:1. Solutions for Color Fringing: What is the recommended method to correct this specific Red/Green separation? If this is caused by band misalignment, is there a standard tool or Python workflow (e.g., using AROSICS or similar) to realign the RGB channels specifically for Visual

Este estudio caracterizó la dinámica espaciotemporal de la línea de costa en Juanchaco, Buenaventura, para el período 2018-2025, y proyectó su tendencia evolutiva para los años 2030 y 2050. La investigación se basó en el procesamiento de un total de 37 imágenes satelitales de la constelación PlanetScope, con una resolución espacial de 3 metros, las cuales fueron sometidas a correcciones radiométricas y atmosféricas. Para la extracción automatizada de la línea de costa, se aplicó el Índice de Diferencia Normalizada de Agua (NDWI), seguido de un proceso de umbralización y vectorización en ArcGIS Pro. Las líneas resultantes fueron analizadas con el Sistema de Análisis Digital de Línea de Costa (DSAS) v6.0, lo que permitió cuantificar el desplazamiento y identificar patrones espaciales a través de 308 transectos generados cada 20 metros. Se calcularon métricas de tasa de cambio como el Desplazamiento Neto (NSM), la Tasa entre Puntos Extremos (EPR) y la Tasa de Regresión Lineal (LRR). Los r

Just looking for some clarification regarding the harmonization process for the 8-band surface reflectance product. I am particularly interested in using the yellow band surface reflectance. Since harmonization is with Sentinel-2, is there any harmonization/correction that occurs to the yellow and green 1 band, which Sentinel-2 does not have? 

Hello, I’ve been working with Dove and Super Dove time series to explore in-season variable rate nitrogen adjustments with private sector stakeholders, where NDVI and other indices are key metrics to characterize in-field variability. In some of the scenes (such as the one shared above) I’ve noticed a visual striping pattern, and I am wondering if there is a way to adjust for this, or to know which satellites may be prone to this to avoid them in our analyses. We will eventually be using imagery over large areas and won’t be able to evaluate each scene visually, so an automated way to 1) adjust for the striping, or 2) know which scenes have them to remove from our time series would be quite valuable. Thank you!- Jyoti Jennewein, USDA-ARS

Hi everyone,I'm conducting a crop monitoring project in southeastern Turkey and comparing NDVI values across three platforms (AWS, GEE, and Sentinel Hub) using the exact same Sentinel-2 tiles and date.During this process, I observed consistent NDVI differences across platforms, even when using the same data product level (e.g., L1C).  Scene MetadataDate: 24 August 2024 Tiles: 37SDA, 37SDB, 37SEA, 37SEB AOI: Same polygon used on all platforms Bands: B04 (Red) & B08 (NIR), scaled to [0–1] as needed NDVI Comparison (Tile 37SDA Example) Platform Product NDVI Mean NDVI Min NDVI Max AWS L1C 0.5206 0.4238 0.5582 GEE L1C 0.52198 0.4475 0.5582 GEE L2A 0.6085 0.5173 0.6458 Sentinel Hub L1C (EO Browser) 0.74 0.56 0.80 Sentinel Hub L2A (EO Browser) 0.85 0.61 0.93  

Hello, https://services.sentinel-hub.com/ogc/fis/xxxxx-19dd-xxx-xxxx-xxxxxxxx?BINS=20&layer=VEGETATION-INDEX-VALUE&RESOLUTION=10m&crs=EPSG:4326&STYLE=INDEX&MAXCC=1&time=2025-06-18/2025-07-06&geometry=POLYGON%28%28-25.4148+31.66437%2C-25.40882+31.67282%2C-25.40641+31.67593%2C-25.40514+31.67734%2C-25.40399+31.67823%2C-25.40248+31.67938%2C-25.4009+31.67985%2C-25.39879+31.68096%2C-25.39597+31.68296%2C-25.39478+31.68443%2C-25.39264+31.68856%2C-25.39153+31.69054%2C-25.39058+31.69259%2C-25.38962+31.69486%2C-25.38833+31.6969%2C-25.38706+31.69934%2C-25.38594+31.70293%2C-25.38365+31.70592%2C-25.37988+31.71129%2C-25.37934+31.7153%2C-25.37925+31.72036%2C-25.37934+31.72297%2C-25.37957+31.72639%2C-25.37948+31.72988%2C-25.37883+31.73381%2C-25.3782+31.73569%2C-25.37846+31.73886%2C-25.3789+31.73999%2C-25.37909+31.74021%2C-25.38139+31.742%2C-25.38423+31.74526%2C-25.38933+31.74358%2C-25.39061+31.74593%2C-25.39183+31.74541%2C-25.39277+31.74656%2C-25.39488+31.74689%2C-25.39736+3

Hi everyone, I recently worked with Planet data for the first time. I downloaded two PlanetScope images from the Planetary Explorer (RGB-IR reflectance and I also chose the option to harmonize images with Sentinel-2)I then calculated NDVI for both images and then the average. I am very surprised by the averages I find. In the center of the image a fire happened in between the two dates so I would expect NDVI to decrease (makes sense). However, I am suspicions of the increases in NDVI I see in other areas, that seem to be the same order of magnitude. While this could be an artifact of NDVI just being quite low in general, I was still wondering if there is an issue with comparing data across difference images taken by different satellites?Here is the code I used to process the data (in R):library(tidyverse)library(sf)library(terra)library(tidyterra)NDVI = function(raster) { ndvi_r = (raster[[4]] - raster[[3]]) / (raster[[4]] + raster[[3]]) return(ndvi_r)}raster_prefire = terra::rast('202

In November’s Agile EO episode, we introduced Analysis-Ready PlanetScope (ARPS)—a new offering that accelerates your analytical workflows with pre-processed, harmonized satellite imagery. Watch the webinar on-demand.  Below are some questions we received during the event and resources to learn more. Questions Question: Is there a technical product sheet for today's products?Answer: The Analysis-Ready PlanetScope Technical Specification is available here. Question: How do you reduce the clouds or select the images with minimal clouds?Answer: Analysis-Ready PlanetScope does not remove clouds. It composites the best available PlanetScope pixel taken over an AOI based on the amount of cloud cover and quality. The cloud mask is produced by creating a cloud-free reference image using a year’s archive of PlanetScope, Sentinel-2, and Landsat.  Question: Can Analysis-Ready PlanetScope data be accessed in Planet Explorer?Answer: No, currently, there is no support for viewing Analysis-Ready Plane

Hello, I wanted to know if Planetscope images have the same footprint. For a defined AOI, is the pixel position maintained for images from different dates?

Dear Planet Company,Hello, I am a fan from China. Recently, a cycling blogger I follow went through a very terrible setback. During his cycling journey, his beloved cat was poisoned and discarded. Since the area was extremely desolate and there were no available surveillance footage, I was wondering if Planet Company could check satellite images or real-time footage within a 5km radius of the following coordinates for the time frame below?Coordinates: 39°11'54" N, 88°55'36" ETime: April 15, 2025, from 16:00 to 19:00 (GMT+8)Thank you for your consideration.

Hello!I have a set of scenes of the same area, but there’s some slight misalignment between them (like 3 or 4 pixels), this usually isnt a problem, but I need the most precission possible for my use case (measuring coastal recession), so even a small misalaignment could change results greatly. This happens between images from different and same sensors, so it isnt a result of using different sensors (at least i dont think so),beacuse i have some that are correctly aligned. Also, i used the same AIO to download the images from PlanetScope, so the images have the same extent and are clipped to the same area.  My question is, is there any way to download scenes that are correctly aligned, or should I fix it manually? (or is there a faster way to automatically align them?)  Thanks everyone!

I downloaded 8-band analytics ready surface reflectance PlanetScope scenes for a study. I want to create a visualization of one of the scenes with QGIS. However, when I load the scene in QGIS as a raster, it doesn’t look like the agricultural field I’m expecting. I made sure to assign the bands as red = 6, blue = 2, and green = 4.This is how the scene looks in Planet Explorerscreenshot of planet explorer showing a selected image in an AOIThis is how the PlanetScope scene looks rendered in QGISQGIS with the PlanetScope scene in the drawing area The scene looks like an odd mosaic of colors. I realize that the resolution of the underlying NAIP image might influence how the scene might be perceived, but honestly, the scene looks like an odd mosaic of colors. How can I get the scene to render in QGIS the way it looks in Explorer?

Hi all,I’m working with PlanetScope SuperDove UDM2.1 data in ArcGIS Pro and I’m trying to better understand how to interpret and visualize clear pixels in the UDM RGB composite.As I understand it, the default RGB band mapping is: Red = Clear Green = Snow Blue = Shadow To work around this, we’re also testing the individual UDM bands using Extract Bands and the Raster Calculator, creating binary layers like:Con("UDM2_B1" == 1, 1, 0) (assuming Band 1 = Clear), so that: 1 = clear pixel 0 = not clear This is giving us a more direct view of which pixels are flagged as usable. Are we on the right track with that approach?I'd love to hear how others: Visualize or validate clear pixels in RGB composites Work with UDM2 bands in ArcGIS Pro or QGIS Apply symbology or classification to quickly identify good pixels for analysis We’re using this for water quality and algal bloom detection, so identifying usable pixels accurately is important for our downstream work.Any advice, workflows, or

Hi,I found some black lines (low values ) in the NIR band of  20200224_152346_83_106b_3B_AnalyticMS_SR. Those lines do not appear in RGB bands, so I think they are not natural features.I m not sure how many files have the similar issue. Would you please check as NIR band is very important to our research. best,Haiyan

Hi. I’ve noticed that in some images (3/3 so far), the udm layer has some shifts across scenes for one same tile/overpass. This complicates the application of cloud masks. Is is something you are aware of? or is it rare and I was just unlucky? 5626519_3264221_2022-05-09_241c_udm25625958_3263610_2022-05-08_241c_udm25626519_3264220_2022-05-09_241c_udm2 

Hello everyone,  I am using PlanetScope Scene images already corrected in surface reflectance (Dove Classic) to assess the temporal changes of the vegetation cover on a specific site. As the site is about 30 km long, I need to use several tiles to cover the whole area.  I have recently noticed that the reflectance values of the pixels of two overlapping images are quite different (even if the images were taken by the same satelitte, at the same time).Do somebody know why do I oberve this ? If yes, do somebody know how can I solve and obtain consistant surface reflectance values between overlapping tiles ? I thank you in advance for your answers, Léo

Hi, I’m having issues with the ‘harmonized’ PlanetScope data products.I have been downloading several such scenes and after saving the extracted data folders on disk, the products seem not be the harmonized versions of the scenes. I posted a related question  in the forum some months ago but I realize that, from my part I correctly choose the data product to be ‘harmonized’ (please see attachment temp_screenshot.jpg) while ordering. Nowhere in the downloaded files (.tif extension, manifest json file) is there an indication of the product being harmonized, it looks like an ordinary surface reflectance composite scene.For reasons I don’t understand, on the only 2 instances where I received properly annotated ‘harmonized’ products, the extracted folder had a different structure (attachment temp_screenshot_2.jpg). Usually each downloaded product gets extracted in a single folder that contains the ‘manifest’ and ‘catalog’ files.I would really appreciate some assistance/ clarifications here.

I am working on a geopolitical science project on a weekly basis, how to get the PlanetScope global image within 30 days but with a low revisit rate? I've noticed the MONITORING PLAN, but a high revisit rate doesn't fit my needs. Thank you!

Hi,I’ve downloaded some 8b sr images, but I found they have some black strips across the image. (see below, band 4 of 20230214_080952_42_2447_3B_AnalyticMS_SR_8bmore obviously in shortwave bands. would you please check?Best,Haiyan 

In March’s Agile EO episode, we introduced Aircraft Detection—a new offering that provides near-daily monitoring of thousands of airfields globally, enabling trends and anomalies to be spotted. Watch the webinar on-demand.  Below are common questions, and questions that we weren’t able to get to during the live event. Our hosts Justin Davis, Sr. Product Manager - Applied Machine Learning, and Adam Van Etten, Principal Data Scientist, have provided answers, plus resources to learn more. QuestionsQuestion: Can you track aircraft in flight? Answer: We can’t say for sure that a given aircraft is the same aircraft from one day to the next, BUT we can track how many aircraft are present at a given airfield each day AND whether the aircraft present are in the same positions as they were before. This can help indicate activity at a given airport/airfield and highlight anomalous behavior. Question: How big of an airplane can you detect?Answer: In our experimentation, we found performance for ai

Hi,I am very new to remote sensing. I got raw images from planet scope for my area of interest through QGIS plugi. however before I calculate NDVI for my area. I need to normalised or scale the bands. I am using this formula lower_percentile = 30upper_percentile = 70y1=float(0.2)y2=float(0.5)def scale(band): # scale values for display purposes    band = band.astype('float64')    x1 = np.log10(float(np.percentile(band[band!=0], lower_percentile)))    x2 = np.log10(float(np.percentile(band[band!=0], upper_percentile)))    band[band==0]=np.nan    band = np.log10(band)    def equations(p):        a, b = p        return (np.log(a)-x1*b-np.log((1-y1)/y1), np.log(a)-x2*b-np.log((1-y2)/y2))    a,b =  fsolve(equations, (1, 1))    band=1/(1+a*np.exp(-b*band))    return band. Can somebody please tell why could be different method for scaling and is there any paper which can recommend for scaling the planet images? 

Hi,We have started testing PlanetScope, but we are unable to retrieve NDVI data for the selected area.In My Collections, we created a Collection with ID, and we added a Subscription to it. The PlanetScope data was successfully loaded—we can see and download it via the web application.However, when we try to generate NDVI using the API endpoint https://services.sentinel-hub.com/api/v1/process, we do not receive any data. The endpoint returns null.Request:{ "input":{ "bounds":{ "properties":{ "crs":"https://www.opengis.net/def/crs/OGC/1.3/CRS84" }, "bbox":[ 13.895467093481912, 49.978376989130496, 13.905815440973406, 49.982298215337835 ] }, "data":[ { "type":"byoc-<collectionId>", "dataFilter":{ "timeRange":{ "from":"2025-03-09T00:00:00+01:00", "to":"2025-03-09T23:59:59+01:00" }