Colour scales / colormaps for satellite imagery vegetation indexes

Understand the different ways of applying color scales to satellite imagery derivatives such as NDVI. And a few tips and gotchas along the way.


Whole text books are written on data visualisation. I’ve not read much of any of them, but I’ve spent quite a bit of time thinking and experimenting with how satellite imagery derivatives such as NDVI are best visualised. There is no one size fits all. Basically the aim is to be able to extract as much information with as little effort and time as possible. As an agronomist, you are never just looking at one field but multiple fields and over the entire season and even comparing to past seasons. This article is to offer some ideas I’ve developed on the subject plus a few tips and gotchas along the way. It’s a bit opinionated and not a text book chapter.

What are we doing here?

There are a few ways to process and display satellite imagery such as natural or true colour, alternative band combinations, spectral indices (including vegetation indexes) and more. In this article I will focus on how spectral indices are visualised.

First, what is a spectral index? A spectral index is a formula designed to take individual bands as inputs and generate a derivative dataset intended to measure or depict a certain physical characteristic of the environment on the ground. For example NDVI takes in two bands - red and near infrared reflectance - into a formula that spits out a single layer where each pixel has a value of -1 to 1. Where, in a perfect world, dense, healthy vegetation would have a value close to 1 and zero vegetation ends up around 0 or a bit below. And then there is everything in between.

If we just had a map of paddock divided up in 10m-by-10m squares (as a grid) with a number representing the NDVI value in the square, it would be time consuming to analyse and it would be hard to grasp the overall trends across the paddock. This is where data visualisation comes in. We can take what is called a colour scale (aka colormap) that applies a colour to each square of the grid based on the NDVI value. There are lots of colour scales and lots of ways to drape the colour scale over the data.

MS Excel Conditional Formatting applies color scales to cells the same way it is applied to vegeation index pixels

Ask these questions

The person interpreting the map should understand at least to some degree how the map published has applied colour to numerical values. More than once data has been misunderstood by a poorly applied colour scale or a user not understanding how to interpret it. Whenever looking at a spectral index visualisation consider asking yourself these questions:

  1. What is the minimum & maximum value in the dataset?
  2. What is the minimum & maximum value on the colour scale?
  3. Is the colour scale applied evenly across the dataset?
  4. Does the colour scale have enough colour changes in it to represent the variability in the data?
  5. Conversely, does the colour scale misrepresent the data with too many colour changes on a dataset with very tight range on the min & max?
  6. Will this colour scale transfer directly to other dates of paddocks you are comparing it to or is the min & max value of the colour change base on the statistics of the dataset?
  7. …there many other things but you get the idea – think this through.

Dynamic vs fixed

Question 6 above mentions the idea of transferring colour scales across datasets so they can be directly compared. I would call this a fixed colour scale. A fixed colour scale always has the same minimum and maximum. The obvious advantage to this is that you can directly compare different dates or fields side by side and the same colour will represent the same value across the board. In addition, the brain often trains itself that a colour means something and having that always change can mean it takes more time to interpret.

The dynamic colour scale is more traditionally seen where the minimum and maximum of the colour scale are set by the statistics in the dataset. For example, the bottom and top 2% of values are clipped or excluded from the dataset as these may be outliers. Then the min and max are identified and applied the colour scale. The advantage of a dynamic colour scale is you are almost always going to be able to extract more variability from the data if the min and max of the colour scale are squeezed together.

My preferred color scale

My favourite color scale is called Turbo. You can read about why it works well on their blog: Turbo, An Improved Rainbow Colormap for Visualization – Google AI Blog. As is, this is my go-to when applying a dynamic colour scale. When in need of a fixed colour scale I take the turbo colourmap and add a high contrast tip at either end i.e. Turbo Tips.

This is an attempt to get the best of both worlds:

  • a fixed colour scale, so comparing different dates and paddocks is more logical,
  • also being able to visualise the changes right through the growth cycle from none to high biomass with a high contrast set of colours.

This works well for detecting emerging crops at the bottom end and is a signal for saturation at the top end.


These explanations are best understood visualized. Look closely at the color map legend in the Turbo Tips column.

The 17 May capture is probably the most interesting as the eastern side of the paddock is beginning to show signs of the wheat emerging.

Wheat paddock planted 9 May 2022. Three dates, with three ways to apply a color scale: dynamic, fixed and fixed with tips

As you can see form the histograms below, the data distribution is very diverse for these three datasets so it is a challenge to apply a single fixed colour scale to all three.

Histogram. Band 1: 2022-05-17, Band 2: 2022-06-08, Band 3: 2022-08-07

Fixed colour scale and data quality

A fixed color scale applied over a period of time is great for tracking progress and comparisons but this only works well with robust data. Thankfully, we now get good quality atmospherically corrected data for Landsat 8/9 and Sentinel 2. It’s safe (?) to take an image from 10 days ago and compare it directly to today. You can visually see or measure physical changes based on increases or decreases in the value of spectral index applied.

Unfortunately, this does not apply equally across all remotely sensed imagery. It’s important to understand if the timeseries imagery has been ground calibrated or processed to be analysis ready if necessary. Drone imagery and even aerial imagery can be particularly bad if left unchecked. Also, remember that there are different levels of processing from Landsat 8/9 and Sentinel 2. Obtain Level 2 to have a good chance at comparing satellite imagery through time.


There is a lot more to be said on this topic but the basic idea is you need to understand that data visualisation can be messy and opinionated. In saying that, as we move towards more imagery, more often, being able to visualise imagery in a way we can perceive what it is telling us quickly and accurately is very important.


Comments powered by Talkyard.

Monitoring glyphosate resistant fallow weeds with Sentinel 2 satellite imagery

Follows along the fallow weed control journey with Sentinel 2 overlayed on high resolution imagery.


It’s well understood that controlling fallow weeds to preserve moisture and nutrition for the following crop is essential for success. What is less known is that the 10m resolution Sentinel 2 imagery is quite capable at detecting the presence of weeds in fallows. You’re not going to detect individual plants, but rather as clusters develop the overall reflectance in the pixel will change, allowing us to map it.


In this example, I have applied the MCARI2 spectral index instead of the normal NDVI. As I’ve mentioned in the past, I find it does a better job and not saturating and less affected by soil color (which will help here). The data has an interpolation applied to smooth out the blocky pixels to make it easier on the eye. The background is a Google Maps high resolution true color satellite image.

The Story

This paddock was 2022 wheat harvested in November. After harvest, some residuals + paraquat were applied followed by a Weedit camera spray to get us on top of the fleabane and other scattered weeds.

Following some rain in early January there was a germination of volunteer wheat in the header trails (plus other weeds). You can see here some interesting patterns develop across the paddock. Some areas the header trail had more wheat germinate than in others.

Copernicus Sentinel 2 using MCARI2 (2023-01-17) in fallow over Google Maps imagery

The next image (2023-01-29) shows other parts of the paddock start to green up – particularly the heavier soils. The volunteer wheat took longer to ‘get up and go’ here. Furthermore, in many places where it had got away early have now a decreased MCARI2 value as they have been affected trying to grow in summer and pushed roots past the header trail into the soil and therefore affected by the flame residual.

Copernicus Sentinel 2 using MCARI2 (2023-01-29) in fallow over Google Maps imagery

To put the wheat out of its misery we sprayed glyphosate on 27th January. Following the spray, this image (2023-02-03) shows almost all the green taken out of the map except for a few places. This remaining green was of course glyphosate resistant populations of barnyard and feathertop rhodes grass. These grasses were present in a few other places as individual plants as well - not significant enough in size or population to show on the imagery.

Copernicus Sentinel 2 using MCARI2 (2023-02-03) in fallow over Google Maps imagery

The Weedit did another round to tidy up these weeds with that latest image showing a tidy paddock (2023-02-11).

Copernicus Sentinel 2 using MCARI2 (2023-02-11) in fallow over Google Maps imagery

Finishing notes

Attempting to detect weeds in fallows is a challenging use case for this imagery. Therefore the color scale is set to be quite sensitive which can lead to some noise, or other issues such as brighter soils or residues seen as weeds.

The way I suggest using imagery for weed monitoring is more as an insurance or an overview rather than a way to task sprays or inspections. Things will definitely start getting out of control if you were to wait until you can see something on a satellite image before you go out and see what it is on the ground. But if you can start to see green areas on imagery – this would indicate higher priority for sure.

Weedit camera sprayer over feathertop rhodes grass


Comments powered by Talkyard.

Comparing PlanetScope and Sentinel 2 satellite data in wheat

Applying MCARI2 spectral index to commercial and best freely available remote sensing data then comparing results

Hot Take: PlanetScope imagery does not perform well in high biomass situations. Where PlanetScope saturates, Sentinel 2 continues to show variability.

Comments section at end of article


Many of us are familiar with Sentinel 2 imagery. It is currently the primary imagery source used in many ag related applications. Sentinel 2 is controlled by the European Space Agency (ESA) and the data is made freely available. It has a 10m spatial resolution with 5 day revisit cycle to any point on earth.

PlanetScope is a commercial imagery provider that images the whole earth almost daily. It has a 3 to 5m spatial resolution.

Last season I decided to experiment with PlanetScope imagery on one paddock to compare it to freely available Sentinel 2 imagery.

Crop details

The crop planted was lancer wheat that went in on 9 May 2022. As you will see in the imagery this crop has a few things going on:

  • Two stage planting due to rain event
  • Water logging through the western part of the field
  • Urea fertiliser rates changed through the middle of field
  • Phalaris weeds choking out wheat in the north western corner - controlled in June

All this makes the data interesting to examine.

The crop average yield was 4.75t/ha with 10.6% protein.


PlanetScope vs Sentinel 2 using MCARI2 in wheat

Data Discussion

It is very clear that in both the August and September acquisitions that the PlanetScope imagery does not detect any variability in the crop for the entire eastern half of the paddock. In the Sentinel 2 imagery the north-south running fertiliser rate affected strip and contour banks are detectable.

Furthermore, in the August imagery the Sentinel 2 image does a much better job at exposing the variability from all the issues in the east side of the field.

The early June PlanetScope image looks more sensible, but it’s important to note the crop has only been established for 4 weeks.

The PlanetScope imagery boasts a higher spatial resolution which is discernible and useful in the June comparison. But this is where any quality advantage ends. The 3 to 5m spatial resolution gives no real benefit of understanding the severity of the issues at hand than the Sentinel 2 10m.

The real advantage when it comes to PlanetScope is the temporal resolution. You can’t really beat daily imagery. With some farms unable to reliably get Sentinel 2 imagery due to consistent cloud, PlanetScope may necessary. Although, if you require imagery late in the season, it’s unlikely that PlanetScope will be much use to you if is totally saturated.

Data processing and cost

Modified Chlorophyll Absorption Reflectance Index 2 (MCARI2) was calculated from both the Sentinel 2 and PlanetScope data. MCARI2 generally performs well at not saturating in high biomass situations. It’s my usual go to instead of NDVI. The output image shows three different dates compared using a fixed color scale across both imagery types and all dates.

PlanetScope imagery is the most interesting commercial provider because they are collecting and archiving imagery of the whole earth all the time. That means you always have the option with Planet to go back in time and there is no tasking required.

I purchased the PlanetScope imagery through Sentinel Hub. Sentienl Hub costs EUR30 / month for a non-commercial license and the PlanetScope imagery cost EUR500 (EUR2.5/ha or AUD$3.85/ha or US$2.70/ha). The imagery is on a subscription type arrangement where you get all the imagery over a 12 month period dropped into a cloud storage bucket that you access through Sentinel Hub.

Once in Sentinel Hub you can access it on their EO Explorer or feed it through to a GIS software like QGIS or ArcGIS as WMTS or similar. There are some technical aspects to consuming imagery like this instead of in a specialised app but it provides a lot more freedom to process imagery how you like. Sentinel 2 imagery is accessed the same way, but there is no cost for the imagery.


In conclusion, these datasets are sourced from very different hardware systems which lead to vastly different outcomes. I do think that PlanetScope is appropriate solution in a high cloud area to make early assessments, for example to examine high N test strips. But moving more than a month or two into the growing season for cereal crops, the PlanetScope is likely to saturate in a positive season. I would not recommend spending extra money on PlanetScope if you have plentiful Sentinel 2 imagery available.


Comments powered by Talkyard.

Waterlogged areas in wheat 2022-06-25

In season crop scouting with satellite imagery

A suggested process with tips and examples for applying satellite imagery to crop scouting using a spectral index such as NDVI

Over time agronomists can get very good at examining the most recent satellite image of a paddock with a familiar spectral index and color scale applied to extract a large amount of information very quickly. It is a tool that improves human productivity and can help them catch issues that they may not have known existed. From a typical ground level inspection, an agronomist may see only 20% of a field and even then, variability in the crop health across the field will be hard to pick up. Imagery gives them a bird’s eye view and enables them to target in field inspections. When using satellite imagery to aid with crop monitoring and more efficient scouting process I would recommend considering the following process.

1. Understand the paddock history

Many paddocks farmed today used to be several smaller paddocks. We can sometimes identify where old paddock boundaries were 10+ years after they were combined. Similarly, if a paddock was split in half for just one season, that split can often be seen in the following crops. It’s important to know this paddock history as it impacts the overall variability. A lot of this history will come to light in step two.

2. Investigate for ‘normal’ variability

You can’t skip this step. You need to take time to understand the ‘normal’ variability that exists in a paddock. After looking at several years of satellite imagery it’s possible to see common trends that persist season to season. We are lucky now to have 5+ years of Sentinel 2 data and almost 10 years of Landsat 8 onwards. There are multiple services that attempt to automate this by taking an image at peak biomass over multiple years and running statistics on each layered pixel to produce a single map which can be useful. I would recommend taking the time to do it manually especially if you have spent little time looking at imagery of the field in the past.

The variability will differ depending on the type of season, crop type and management. An unusually wet season causes waterlogging on low lying areas cause plant death and low production. These same areas may likely to be highest producing in a very dry year. Although it can differ by season type, there is almost always some consistency over the years in how variability of crop growth persists throughout different seasons.

A few tips when doing this:

  • Don’t always just look for the peak of the growth cycle to identify normal variability. Often at peak biomass much of the paddock may be saturated appearing to be uniform across a large area. See if there is some imagery available a few weeks before the peak and this may give a flatter distribution of values across a paddock identifying more variability.
  • Make sure you understand how the software is visualising the imagery. Some will use a static color scale where the color you see always represents the same value, and others will always stretch the color to match the data in the field. There are pros and cons to both of these but it’s important to be comparing apples with apples. A dynamic scale is OK if the range is sufficiently wide enough as well are mostly looking for the patterns here instead of absolute values.
  • Try to understand what has caused there to be variability in the paddock. Other imagery sources can help here. See if you can find a bare earth satellite image or look at the high resolution image on Google Earth – does it simply follow a soil color trend? If not, that is interesting.
  • What’s normal isn’t always what is acceptable. What I mean by this is, there might be a spot in a paddock that always have bad ryegrass showing that it’s ‘normal’ for this area to indicate high plant growth but it is actually detecting the weeds.
  • See if the variability pattern moves through the fence line. You need imagery of the neighbouring paddocks for this. If it stops at the fence line, ask yourself why.

3. Inspect the latest image

Armed with the knowledge gained in step two when looking at the latest image, here we look at it through two lenses

  1. Trying to spot anomalies. An anomaly is where the imagery bucks the normal variability – either higher or lower than normal and often in an unusual pattern. Your job is to now see if you can explain them just by using your knowledge of the field and the data in the satellite image. And then verify your assessment when in the field.

A typical Sentinel 2 or Landsat 8 with NDVI or similar spectral index applied has been known to express some of these anomalies:

  • Weed infestations expressed as higher NDVI values
  • Spray drift
  • Waterlogging
  • Hail damage
  • Large areas of disease such as ascochyta blight (although if this imagery can capture this you have problems)
  • Feral pig damage
  • Nutrition deficiencies
  1. Targeting a low, mid and high plant growth areas. Examples of why to target these different areas include:
  • Desiccation decisions
  • Targeting high biomass areas as early insect pressure starts here
  • Harvest timing

Don’t forget to inspect closely anywhere you know a trial or accidental trial has been conducted. Accidental trials are where maybe the fertiliser bin ran out, the fungicide ran out, the planter was planting double rate etc.

4. Consider Timed difference / change maps

Inspecting how the crop has changed over a period of time is also valuable to understand the crop development. Some software allow you to create a map that shows the change on images captured on different dates. For a 10 day timed difference map it is very simple formula of [current NDVI] – [10 day old NDVI]. Positive values are increased crop health or biomass and negative values are reduced. This new piece of information provides another perspective to examine crop growth. A single image will only give you a total measurement. A difference map provides direction and amount of change. It’s common for different soil types to impact the speed at which plants will move through growth stages.

5. Plan your next trip to the paddock

Now that you have understood as much as you can about the paddock from the imagery you can visit the paddock and make sure all anomalies can be explained and you have investigated the right places to gain a more accurate representation of the crop. Understandably, the imagery doesn’t account for all issues or variability in the paddock but it puts you leaps and bounds ahead of if you had not used it at all.

Other gotachas and tips:

  • If something ever looks strange always consider that the imagery could be at fault. E.g. cloud shadow is often missed and this will play havoc with NDVI values causing what looks like anomalies
  • Some in crop sprays can impact leaf angle and this can alter the value. An example is Tordon 242 in wheat and barley.
  • NDVI is not the only spectral index to consider. It’s worth testing out several available algorithms. Some others such as MCARI2 can give similar results to NDVI but won’t saturate to the same extent in high biomass crops.


Comments powered by Talkyard.

In field experimenting with satellite imagery in agriculture. What’s holding us back?

Investigating the state of self-directed experimentation and exploration using satellite imagery datasets in agriculture and identifying potential obstacles.

This is my perspective drawn my own experience as a grain farmer and having built tools for satellite imagery in the past. My journey started out as research into drone imagery in 2013 and led to a clear focus on the applications of the freely available Landsat 8 and later Sentinel 2 multispectral satellite data.


When it comes to how satellite imagery is applied to agriculture, it seems that up until most recently, many that provided satellite imagery usually offered just one, at most five spectral indices, with by far the most common being Normalised Difference Vegetation Index (NDVI). Clearly this is starting to change with more bandwidths available and the work going into machine learning that aims to provide some additional insights. NDVI is definitely the low hanging fruit when it comes to the types data that is available (medium spatial resolution (10 to 30m), multispectral, medium width bands) as it does a good job of estimating vegetation properties such as leaf area index (LAI) or more broadly crop health.

The fact that NDVI is so good at giving a broad spatial indicator of crop health leads many to believe that NDVI is in fact all there is to satellite imagery. The End. But the issue here is that an enormously complex procedure with unlimited options for processing and visualizing the data captured has been reduced to a somewhat opinionated idea that a particular algorithm and color scale is what you need. This is GREAT when it comes to selling a ‘solution’ to a busy agronomist. The idea being let the remote sensing experts figure out what the agronomists need to do their job and sell it to them. It’s a solid option.

The alternative

I’d like to think about an alternative where the agronomist is empowered to ‘do the work’ or at least have the option to when they need to dig deeper. Let’s say you combined an experienced agronomist or farmer with the power to test out 5 different spectral indexes over a field. They may discover that EVI or MTVI2 deals better with the impacts of wet soil on a cotton field that had just been irrigated before the latest image acquisition or that specific leaf and stem responses of herbicide drift are most noticeable in one algorithm over another. They are continuously on the ground and able to compare what the analysis tells them versus what reality is.

Sure, these results are not going to be peer reviewed ‘science’ but they are definitely impactful and can drive formal research into that direction or some may want to build up some IP around investing in better understanding lesser known spectral indexes to offer better solutions to their clients.

Going further, the red edge bandwidths in Sentinel 2 have allowed for nitrogen estimation algorithms. It could be that slow uptake with these is because some of the solutions built and sold are black boxes that don’t allow for self-directed experimentation. Again, it makes sense that an innovator comes in, learns about the technology, and sells the ‘solution’ to the agronomist but discussions I’ve had with some agronomists is that they would like to have more control over that box or at least be able to look inside.

Risks and obstacles

One risk is an agronomist making a decision based on a pattern they think they are seeing or some other misguided insight that is not there. I’d argue that this happens with standard NDVI and that encouraging more experimentation and looking in the box will lead to better informed agronomists. Therefore, the obstacle here is the agronomists current technical understanding of satellite imagery data and process. A further obstacle is time to allocate to these types of experiments and upskilling instead of just always defaulting to NDVI. But as remote sensing becomes more prevalent in agriculture a well-informed agronomist should probably have the skillset required to understand this process. Also, time invested in understanding satellite imagery can usually be offset by human productivity gains.

Another factor hindering exploration and experimentation may be the focus on AI/machine learning as the solution. Despite the potential benefits, this emphasis may overshadow the vast opportunities for discovery and innovation through field experimentation by skilled agronomists using the full range of spectral indices.

Ultimately, the extent to which a farmer or agronomist uses satellite imagery is their choice. However, it is hoped that this information will encourage them to consider the available options more thoroughly.

Did you know there are 100+ spectral indices available (Awesome Spectral Indices).


Comments powered by Talkyard.

Applications of satellite imagery for agricultural professionals

Satellite imagery can enhance human productivity, monitor & benchmark crops, help with input allocation and support historical & land management applications

Satellite imagery has been used in agriculture for decades, but in recent years it has become more popular with the launch of new satellites by the European Space Agency that are helpfully designed for agricultural monitoring. This has made the data more frequent and allowed companies to develop applications and services that make it easier for agronomists and farmers to access and use the imagery.

This article will draw on a Twitter poll I ran last year that asked “If in agriculture, Where do you find most value with satellite imagery?”. I provided three response options based on my own experiences and asked participants to comment with further answers. To be clear, this article focuses on production side – that is farmers and agronomists, not grain marketing, regional crop forecasting etc. Farmers could use satellite imagery for grain marketing too, but that’s another topic.

The poll

The four poll options with outcome were:

  1. In the field scouting - 20.6%
  2. In the office, scout prep – 39.4%
  3. Input rates, Variable Rate Application – 33.1%
  4. Other – 6.9%

Let’s talk a bit more about each application remembering the poll question was framed around value.

  1. In field scouting - I take this as having your device with you when out inspecting crops. One example might be visiting paddocks on a routine basis. When arriving in field, using GPS location on an NDVI map of the paddock, see if the area you are inspecting is representative of the rest of the paddock.

  2. In the office, scout prep - Planning where you will go when out in the field before you get there. It makes a lot of sense to take a birds eye view of what is happing on the ground before you arrive. You can then target your inspections depending on crop type crop stage. For example, making sure you target high and low biomass areas of the field as the higher biomass areas may be more susceptible to insect attacks earlier. Preparing in the office gives you the added advantage of having access to other information that would be good to know when in the field such as rainfall distributions, crop rotation and yield history.

  3. Input rates which include variable rate application - This is taking the satellite imagery data and using it to apply input rates differently based on the data or some sort of derivative. This could include fertilizer or herbicides. Most new machinery is capable of this. It is interesting that this answer only took in 33% of responses. Maybe the audience is biased, or it could just be that the less technical applications of satellite imagery may just add more value.

  4. Other - A review of the comments sees discussion relating to harvest decisions, monitoring field trials, and inspecting historical development of the land.


It’s interesting to see the breakdown of the responses here and consider if people obtain most value in part because of the success and limitations of the tools available to and put in front of them. For example, when Agworld added a frequently update imagery layer suddenly many more people were now able to see variability within their fields that they may have not otherwise noticed. Now every Agworld subscriber had access to in office and in field satellite imagery to some degree and could ascertain it’s usefulness.

Many ag professionals are seeking out the next way to improve the service they provide, or the operation they manage and satellite imagery is a natural fit that leaves them wanting more.

Reframing the categories

Thinking further about applications of satellite imagery for agricultural professionals, it can probably be reframed in a more helpful way to these four categories:

  1. Enhancing human productivity
  2. Monitoring & benchmarking
  3. Optimising Input allocation
  4. Historical & land management applications

Clearly there is still some overlaps here. But lets look at each more closely:

1. Enhancing human productivity

As humans, we want to be as efficient as possible. Imagery enables this with the infield and in office scouting. Agronomists can make their inspections more targeted. It costs a lot to have humans on the ground, so they should be sent to where they are needed most. Improving the toolset to do this job can further increase productivity.

2. Monitoring and benchmarking

Sometimes you can monitor change better from space than humans on the ground, especially consistently over a large area. Many satellite sensors are always on capturing and archiving what they ‘see’ even if you have not planned it to be so. Understanding crop variability, comparing to previous crops in the same field and same season crops in different fields allows for much better management outcomes and better-informed decision making. The harvest timing mentioned above fits in here as does inter-season anomalies (e.g. this area usually performs very well but is falling behind this year). An added advantage is that the data is stored in raw formats so as spectral indices improve you can go back in time and apply better algorithms to old imagery. Monitoring includes fallow management as well such as weed infestations.

3. Optimise input allocation

This brings us back to the variable rate chemical and fertilizer application. There are many examples where satellite imagery has been used on it’s own, but more frequently with other data sources to better allocate fertilizer to either even out yields or get best return on investment. This could be using a simple vegetation index such as NDVI or using soil color as a proxy representing some soil characteristic.

4. Historical & land management applications

With archives going back well into the 80s, satellite imagery is very useful for understanding the history of the land. For example, sometimes variability within a paddock can be attributed to multiple paddocks with different histories being combined into a single paddock. Other applications here are investigating the movement of flood water, researching potential property purchases and spotting where neighboring drift risks are.

This article has taken a quick Twitter poll and given me pause to think about how agricultural professionals apply satellite imagery in their businesses. I have come up with four categories that I think most specific use cases can fall into. It’s good to think about this because it shapes how we think about committing time to exploring satellite imagery as a tool to increase the overall profitability of your business. An example mindset change could be: Don’t dismiss satellite imagery because you think variable rate won’t work on your farm or for your clients. Much of the value in satellite imagery is in the enhancement of human productivity. The converse is, satellite imagery can’t solve all your problems so don’t dive in blinded by hype.


Comments powered by Talkyard.