Notes from the Field

From Space to Farm

April 26th, 2021 by Estefania Puricelli (NASA Harvest), Mary Mitkish (NASA Harvest), Inbal Becker-Reshef (NASA Harvest)

How Earth observation technologies are revolutionizing global agri-food systems.

Nowadays, various forms of technology play a fundamental role in our daily routines. From the use of GPS to navigate to different places, to sharing pictures using just our smartphones, to automatic vacuum cleaners, there are endless examples. Even when it comes to the food we eat there have been so many technological advances and an immeasurable amount of research developed, particularly in the past few decades.

But one common technological thread that we can find within all of these different aspects of our lives is Earth Observation Technologies (EOT) and remote sensing. Numerous Earth observing (EO) satellites have been launched into space by NASA and other international space agencies within the last decade, serving to collect (or “remotely sense”) data about our home planet, which helps experts around the world to better understand our ecosystems and environment. We’ll take a look at agricultural production, international food markets, and global food security as an example of the importance of this remotely sensed Earth observation data.

There are several steps and many factors involved from the time a crop is grown on a plot of land to the availability of certain crops and the price volatilities eventually seen in the corresponding food market system. Because of the complicated paths of the agricultural supply chain, it is often easier to understand this relationship if we think about it as a collective “agri-food system.” Over the past decades, agri-food systems have evolved in so many aspects, but so have the EO technologies that make it easier to understand and monitor every step of this complex chain, bringing transparency and efficiency to the overall system. According to the United Nations definition, the food system includes many different factors such as: food-related resources, various food system inputs, production, transport, processing, manufacturing, retailing, and food consumption, all in addition to the overall agri-food system impacts on environment, health, and society. Many of the changes in our food systems are attributed to external and internal forces as well as feedback mechanisms among these forces. 

Let’s start from the beginning—from the farm and from the plot. With the help of satellites and EOT, producers have a better understanding of weather patterns and can plan the optimal time to sow their land. With GPS-based technologies, producers can use precision agriculture to specifically apply only the needed amount of fertilizers, herbicides, and seeds. Once everything is in the ground, farmers can remotely monitor how the crops are developing from anywhere in the world, and they can even estimate the potential yield they can expect at harvest time months in advance of actual harvesting dates. Such tools are extremely important for successful financial planning. While those crops are still developing, we can use EOT to monitor agro-meteorological conditions such as temperature and precipitation, and their impacts on crop conditions—all of which help us understand if today’s conditions are following the average trends seen in previous seasons. If anomalies occur, the EOT data can warn us well in advance of a potentially catastrophic harvest season which enables earlier mitigation actions.

Example of crop charts showing the 2019 growing season in the United States. The season began under mixed conditions due to wet and cooler than average conditions. Heavy rainfall along with spring meltwaters saturated and flooded many fields, leaving farmers unable to conduct sowing until later in the spring. High rainfall values and very high soil moisture values through June combined with lower than average temperatures resulted in sowing being delayed and then a slow start to crop growth. The delayed sowing and slow start to crop development can be seen in the NDVI plot by the month delay in the increase in NDVI values. Near the end of the season, temperatures stayed above normal, helping the maize crop receive additional heat units for development. During harvest, an uptick in rainfall can be observed at the start of November, potentially hampering harvesting operations and increasing grain moisture levels. Overall, due to the wet and cool start to the season, there was a reduction in total sown area along with a reduction in yields compared to the previous year. Image c/o Ritvik Sahajpal.

Meanwhile, as that same crop is growing, many different market actors around the world are trying to estimate how much of that crop will be successfully produced, not only in that specific region but also throughout the whole country and elsewhere around the globe. Consequently, accurate early estimates of crop area and crop yields are fundamental to the efficient and transparent functioning of global agricultural markets. And guess what? Remote sensing technologies play a critical role here too, providing key pieces of information for analyzing and developing estimates at different scales for crop area and yield, making use of NASA satellite data from missions such as MODISLandsat-8, and SMAP, with additional launches on the way (i.e. NISARLandsat-9). 

At a regional level, crop area estimation can also be collaborative. With a simple picture from a smartphone, the average person—meaning those of us who are not agricultural scientists or economists—can now collaborate with crop mapping experts using newly developed artificial intelligence and machine learning applications. For example, novel processes developed by NASA Harvest are leveraging the massification of smart phones, enabling citizen scientists anywhere in the world to assist in gathering pictures of crops, contributing enormously to the accuracy of the models. Image c/o Hannah Kerner.

At a national level, having accurate and timely information helps policy makers to enact more suitable mitigation plans in case they need to take action if there is an unusual shock to the food system (i.e. extreme weather events, food price changes, a global pandemic, etc.), not only for countries whose economies depend on those crops to be exported but also those countries who rely on imports for their food security. EOT can also help to put many farmers literally on the map, and provide policymakers with timely tools and resources to help them. National governments can assess various crop situations using EOT and are currently monitoring the crop conditions with existing National Crop Monitors. Because the agricultural system on a whole is so dynamic, remote sensing technology can also help update estimates of crop production at a national level as the state of the agrifood system changes. 

At a global level, with the help of information provided by satellite data, the early warning community (including the GEOGLAM Crop Monitor for Early Warning and various humanitarian organizations) have a better understanding of the current situation and can utilize early warning information for early action to more efficiently allocate aid where and when needed. Crop production estimates play an important role in price volatility in different markets, both domestically and internationally, which highlights the need for accurate, cost-effective, and frequent agrifood system monitoring. International communities, such as the Agricultural Market Information System (AMIS), have been launched by the G20 in an effort to monitor commodity price volatility. For example, AMIS publishes a crop monitor bulletin in their monthly reports as a way of providing more transparency into agricultural markets. Timely and accurate assessments of crop harvest quantities can have a positive impact in avoiding extreme price volatility. 

But going back to our crop, remote-sensing data and advanced computing capacity improve yield estimates, subsequently improving the financial planning of the producers (i.e. both small- and large-scale farming operations). Remote sensing technologies also improve field-scale nutrient management, not only helping improve sustainability of crop production but also saving on costs for the farmers. Accurate crop area estimates, especially those estimates with a regional approach, help different types of companies—including seed providers, fertilizers, herbicide producers, agriculture services, machinery companies, and many others—to better plan their marketing and distribution strategies. This information creates a more efficient allocation of resources, with benefits also being seen in often under-represented rural areas.

Moving along the food cycle to the post-harvesting stage, if there was a problem with the harvested crop then insurance providers can use remote sensing technologies to assess the situation from anywhere, minimizing cost and emissions of visiting the plots themselves. Remarkably, remote-sensing data can reduce the transaction costs associated with monitoring traditional insurance contracts, reinvigorating rural finance markets. 

But the role of remote sensing technology doesn’t finish when the crop is harvested. Once the crop is out of the ground and for example, sent to the grain elevator, we can track the exact location of the vessels on which those grains are traveling and their destinations. Most recently, we were able to use Planet satellite images to spot the movements of the cargo ship that halted global trade and created a massive bottleneck in the global supply chain. 

Overall, Earth observation technologies are making the interlinkages of the complex and sometimes fragile agrifood systems more transparent, accurate, and efficient, while also helping to reduce transaction cost and shedding light on the information asymmetry challenges. It almost goes without saying that science, innovation, and technology have huge impacts on understanding changes to food systems. Markets, trade, and related infrastructures—increasingly combined with digitization—are today cutting across internal and external drivers of food systems’ change (Von Braun, 2020) and digital technologies will undoubtedly continue to increase efficiency in the design and delivery of agricultural policies (Schroeder, Lampietti, & Elabed, 2021). EOT has the capacity to enable a rapid assessment of different shocks, providing a powerful tool for decision makers across the agricultural, government, and humanitarian spectrums.

References

Von Braun, J. A. (2020, October 26). Food Systems – Definition, Concept and Application for the UN Food Systems Summit. 

Schroeder, K., Lampietti, J., Elabed, G. (2021, March 16). What’s Cooking : Digital Transformation of the Agrifood System.

Agricultural Monitoring Gets GLAMorized

March 19th, 2021 by Alyssa Whitcraft (NASA Harvest), John Keniston (NASA Harvest), Mary Mitkish (NASA Harvest)

Satellite Data for Agricultural Monitoring

Food security and agriculture is probably not the first thing that comes to mind when you think about satellites being launched into space and orbiting planet Earth. You might even be surprised to learn that NASA, best known for its space exploration, actually has over a dozen satellite missions dedicated to monitoring food production, land changes, and vegetation. Truth be told, the data provided by these Earth observing satellites provides critical information for analyzing the state of food production and food security around the world. From space, we can see things like the NDVI (namely, green light reflectance) of plants which is indicative of crop health, crop damage resulting from natural disasters (such as the 2020 Iowa derecho), and even the amount of moisture stored deep within farmland soil. However, compiling these large satellite datasets into deep time series to monitor interannual and within-season changes in vegetation requires a lot of skill, computational power, and time.

The Legacy Global Agricultural Monitoring System Gets an Update

In the early days of satellite Earth observations, the University of Maryland worked together with NASA and USDA to develop the first web-based platform to enable near-real-time monitoring of global croplands, enabling users across the globe to track crop conditions as growing seasons unfolded (re. Monitoring Global Croplands with Coarse Resolution Earth Observations: The Global Agriculture Monitoring (GLAM) Project). After years of operational use and a lot of valuable feedback from partners, the time came to redesign this system – known as Global Agricultural Monitoring or GLAM – to be faster, more flexible, and to capitalize new datasets coming online and new computing architectures available. Thanks to funding from NASA ESDS and NASA Applied Sciences, the team at NASA Harvest (NASA’s Food Security and Agriculture Program) has accomplished just that.

New GLAM System Features, Datasets, and Functionalities

Now lightning-fast due to back-end developments that drastically reduce processing time, the new GLAM system includes many new functions. Users can access the publicly-available web-interface from anywhere in the world, as all processing takes place on “the cloud” and does not rely on local bandwidth to compile datasets. They can use the interface to pan around the globe to a region of interest. They can select an administrative boundary or draw a custom polygon to investigate. They can select from a variety of cropland and crop type masks to target relevant croplands, and then create custom time series charts with the ability to calculate mean and anomaly for datasets over time. Because cloud cover is a common issue in many agricultural regions and cultivation periods, users can customize their cloud cover tolerance in plotting and displaying imagery as well. Furthermore, users also have the ability to overplot crop calendar information on their time series plots, which provides important context to compare crop conditions between years.

In addition to these new functions and features, the interface includes multiple new datasets to help analysts glean insight into the drivers behind anomalous crop conditions throughout the world. Currently, the new GLAM system includes 8-day and 16-day NDVI datasets from NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS), CHIRPS Precipitation datasets from the University of California Santa Barbara Climate Hazards Center, Soil Water Index from the Copernicus Global Land Service, and Temperature datasets from NASA’s MERRA-2 product, with more datasets on the way.

Example outputs from the Conab Brasil customized GLAM interface.

In addition to the existing global interface, there are also national GLAM system implementations planned and already operational. First up is the Conab Brasil customized GLAM interface, which was developed and tested hand-in-hand with NASA Harvest counterparts at Conab. Conab is a public company, operationally mandated by the Ministry of Agriculture, Livestock and Food Supply to produce area, yield and production estimates regarding several major commodity crops to the Brazilian government. While users can still view and implement all of the same types of datasets offered in the global system, the Brasil GLAM website offers additional features. While the global site does include regional statistics at the subnational level, the Brazilian site goes beyond the subnational level. In response to Brazilian administrative regional needs, this application includes extra Brazil-specific crop masks as well as extra levels of analysis.

What’s Ahead

The updated GLAM system has already been widely used to flag potential crop impacts especially in Argentina, as featured by the country’s largest media outlet La Nacion. In addition to the system’s current capabilities, planned features include the ability to upload custom geometry (for example, shp, kml, geojson) to retrieve dataset statistics and visualization of dataset anomaly in order to provide users with an indication of the relative performance of a crop over time. The team is also preparing to integrate moderate resolution satellite data sets, for example LandsatSentinel, and the Hybrid Landsat-Sentinel products, to move us into this new era of continuous land monitoring at 30 meters or finer resolution. Additionally, the serverless architecture enables us to quickly spin up and launch new GLAM systems for other regions and users. 

Are you interested in your own GLAM system? Contact project PI Alyssa Whitcraft.

How We Accomplished It

By using Amazon Web Services (AWS) and “serverless” architecture, the NASA Harvest team has been able to create both a web application and application programming interface (API) that provides on-the-fly data projection, masking, color table application, image differencing, and statistics calculation. As a result, it is not necessary to pre-generate all permutations of the NDVI datasets that would previously have been generated in on-premises architecture. Likewise, it is also not necessary to reproject the global NDVI datasets with the new GLAM system. The on-the-fly capabilities reduce the storage demand to the volume of only the NDVI files (less than ten terabytes) as opposed to the hundreds of terabytes required by the previous on-premises architecture version. In addition, because these functions are done on the spot, the collection of datasets, crop masks, and color ramps can be arbitrary. Therefore, the system does not need to be limited to NDVI and can be expanded to include precipitation, soil moisture, or any other raster dataset.

In addition to these improvements made to the system architecture, the new GLAM system boasts a modern web map design, utilizing a variety of code frameworks and libraries including Django, Leaflet, and HighCharts.