Tag: data

K.V. Naga Madhuri, Principal Scientist for Soil Science at Acharya N. G. Ranga Agricultural University (front), explains soil spectra during the opening of the soil spectroscopy lab at the Regional Agricultural Research Station in Tirupati, Andhra Pradesh.

New Soil Intelligence System for India provides high-quality data using modern analytics

Written by on December 4, 2018. Posted in Features.

NEW DELHI (CIMMYT) — The new Soil Intelligence System (SIS) for India will help the states of Andhra Pradesh, Bihar and Odisha rationalize the costs of generating high-quality soil data and build accessible geospatial information systems based on advanced geostatistics. The SIS initiative will rely on prediction rather than direct measurements to develop comprehensive soil information at scale. The resulting data systems will embrace FAIR access principles — findable, accessible, interoperable, and reproducible — to support better decision-making in agriculture.

SIS is a $2.5 million investment funded by the Bill & Melinda Gates Foundation. This initiative is led by the International Maize and Wheat Improvement Center (CIMMYT), in collaboration with numerous partners including the International Food Policy Research Institute (IFPRI), World Soil Information (ISRIC), the Andhra Pradesh Space Applications Center (APSAC), and the state governments and state agriculture universities of Andhra Pradesh and Bihar. The initiative runs from September 2018 through February 2021.

“SIS will make important contributions towards leveraging soil information for decision-making in Indian agriculture by devising new soil health management recommendations,” explained Andrew McDonald, CIMMYT’s Regional Team Leader for Sustainable Intensification and Project Leader for the Cereal Systems Initiative for South Asia (CSISA). Researchers and scientists will combine mapping outputs with crop response and landscape reconnaissance data through machine-learning analytics to derive precise agronomy decisions at scale.

Farmers will be the primary beneficiaries of this initiative, as they will get more reliable soil health management recommendations to increase yields and profits. SIS will also be useful to state partners, extension and agricultural development institutions, the private sector and other stakeholders who rely on high-quality soil information. Through SIS, scientists and researchers will have an opportunity to receive training in modern soil analytics.

The SIS initiative aims to facilitate multi-institutional alliances for soil health management and the application of big data analytics to real-world problems. These alliances will be instrumental for initiating broader discussions at the state and national levels about the importance of robust data systems, data integration and the types of progressive access policies related to ‘agronomy at scale’ that can bring India closer to the Sustainable Development Goals.

CIMMYT scientist Shishpal Poonia places a soil sample on the Tracer instrument for soil spectroscopy analysis.

Better soil analysis

Spectroscopy enables precise soil analysis and can help scientists identify appropriate preventive and rehabilitative soil management interventions. The technology is also significantly faster and more cost-effective than wide-scale wet chemistry-based soil analysis.

As part of the CSISA project, led by CIMMYT and funded by the Bill & Melinda Gates Foundation, two new soil spectroscopy labs were recently set up in Andhra Pradesh and Bihar, in collaboration with the state departments of agriculture. One lab is now operating at the Regional Agricultural Research Station (RARS) in Tirupati, Andhra Pradesh; and the other one at Bihar Agricultural University (BAU Sabour), in Bhagalpur, Bihar.

“The support from CIMMYT through the Gates Foundation will contribute directly to bringing down the cost of providing quality soil health data and agronomic advisory services to farmers in the long run,” said K.V. Naga Madhuri, Principal Scientist for Soil Science at Acharya N. G. Ranga Agricultural University. “We will also be able to generate precise digital soil maps for land use planning. The greatest advantage is to enable future applications like drones to use multi-spectral imagery and analyze rapidly large areas and discern changes in soil characteristics in a fast and reliable manner.”

Under the SIS initiative, soil spectroscopy results will be validated with existing gold standard wet chemistry methods. They will also be integrated with production practice data collected from the ground level, through new statistical tools.

Precise predictive models

Drawing information from a limited number of soil observations from a sample dataset, digital soil mapping (DSM) uses (geo)statistical models to predict the soil type or property for locations where no samples have been taken.

“These ‘unsampled locations’ are typically arranged on a regular grid,” explained Balwinder Singh, CIMMYT scientist and Simulation Modeler, “so DSM produces gridded — raster — soil maps at a specific spatial resolution — grid cell or pixel size — with a spatial prediction made for each individual grid cell.”

“Adopting DSM methods, combined with intelligent sampling design, could reduce the strain on the soil testing system in terms of logistics, quality control and costs,” noted Amit Srivastava, a geospatial scientist at CIMMYT. “Improving digital soil mapping practices can also help create the infrastructure for a soil intelligence system that can drive decision-making at scale.”

In partnership with state government agencies and the Bill & Melinda Gates Foundation, CIMMYT will continue to support the expansion of digital soil mapping and soil analysis capacity in India. The CSISA project and the SIS initiative are helping to deliver soil fertility recommendations to farmers, an important step towards the sustainable intensification of agriculture in South Asia.

For more details, contact Balwinder Singh, Cropping System Simulation Modeler, CIMMYT at Balwinder.SINGH@cgiar.org.

An example of digital soil mapping (DSM), showing pH levels of soil in the state of Bihar. (Map: Amit Kumar Srivastava/CIMMYT)

View of the interface of the Maize-Seed-Area app on mobile phones and tablets. (Photo: CIMMYT)

Are advisory apps a solution for collecting Big Data?

Written by Rodrigo Ordóñez on October 2, 2018. Posted in Blogs.

Big Data is transforming the way scientists conduct agricultural research and helping smallholder farmers receive useful information in real time. Experts and partners of the CGIAR Platform for Big Data in Agriculture are meeting on October 3-5, 2018, in Nairobi, Kenya, to share their views on how to harness this data revolution for greater food and nutrition security.

Jordan Chamberlin, Spatial Economist at CIMMYT, will give his insights on best practices on electronic data capture on October 4, 2018.

NAIROBI (Kenya) — Agronomic researchers face several challenges and limitations related to data. To provide accurate predictions and useful advice to smallholder farmers, scientists need to collect many types of on-farm data; for example, field size, area devoted to each crop, inputs used, agronomic practices followed, incidence of pests and diseases, and yield.

These pieces of data are expensive to obtain by traditional survey methods, such as sending out enumerators to ask farmers a long list of questions. Available data is often restricted to a particular geographical area and may not capture key factors of production variability, like local soil characteristics, fertilizer timing or crop rotations.

As a result, such datasets cannot deliver yield predictions at scale, one of the main expectations of Big Data. Digital advisory apps may be part of the solution, as they use crowdsourcing to routinize data collection on key agronomic variables.

The Taking Maize Agronomy to Scale in Africa (TAMASA) project has been researching the use of mobile apps to provide site-specific agronomic advice to farmers through agro-dealers, extension workers and other service providers.

At CIMMYT, one of the research questions we were interested in was “Why are plant population densities in farmers fields usually well below recommended rates?” From surveys and yield estimates based on crop-cut samples at harvest in Ethiopia, Nigeria and Tanzania, we observed that yields were correlated with plant density.

What was making some farmers not use enough seeds for their fields? One possible reason could be that farmers may not know the size of their maize field. In other cases, farmers and agro-dealers may not know how many seeds are in one packet, as companies rarely indicate it and the weight of each seed variety is different. Or perhaps farmers may not know what plant population density is best to use. Seed packets sometimes suggest a sowing rate but this advice is rather generic and assumes that farmers apply recommended fertilizer rates. However, farmers’ field conditions differ, as does their capacity to invest in expensive fertilizers.

To help farmers overcome these challenges, we developed a simple app, Maize-Seed-Area. It enables farmers, agro-dealers and extension workers to measure the size of a maize field and to identify its key characteristics. Then, using that data, the app can generate advice on plant spacing and density, calculate how much seed to buy, and provide information on seed varieties available at markets nearby.

Maize-Seed-Area is developed using the Open Data Kit (ODK) format, which allows to collect data offline and to submit it when internet connection becomes available. In this case, the app is also used to deliver information to the end users.

Advisory apps usually require some input data from farmers, so advice can be tailored to their particular circumstances. For example, they might need to provide data on the slope of their field, previous crops or fertilizer use. Some additional information may be collected through the app, such as previous seed variety use. All this data entered by the user, which should be kept to a minimum, is routinely captured by the app and retrieved later.

Hello, Big Data!

As the app user community grows, datasets on farmer practices and outcomes grow as well. In this case, we can observe trends in real time, for instance on the popularity of different maize varieties.

In a pilot in western Kenya, in collaboration with Precision Agriculture for Development (PAD), some 100 agro-dealers and extension workers used the app to give advice to about 2,900 farmers. Most of the advice was on the amount of seed to buy for a given area and on the characteristics of different varieties.

Data showed that the previous year farmers grew a wide range of varieties, but that three of them were dominant: DK8031, Duma43 and WH505.

Preferred variety of maize for sample farmers in western Kenya (Bungoma, Busia, Kakamega and Siaya counties), February-March 2018.

A phone survey among some 300 of the farmers who received advice found that most of them anticipated to do things differently in the future, ranging from asking for advice again (37 percent), growing a different maize variety (31 percent), buying a different quantity of seed (19 percent), using different plant spacing (18 percent) or using more fertilizer (16 percent).

Most of the agro-dealers and extension workers have kept the app for future use.

The dataset was collected in a short period of time, just two months, and was available as soon as app users got online.

The Maize-Seed-Area pilot shows that advisory apps, when used widely, are a major source of new Big Data on agronomic practices and farmer preferences. They also help to make data collection easier and cheaper.

TAMASA is supported by the Bill and Melinda Gates Foundation and is implemented by the International Maize and Wheat Improvement Center (CIMMYT), the International Institute of Tropical Agriculture (IITA), the International Plant Nutrition Institute (IPNI) and Africa Soil Information Service (AfSIS).

How a seed bank in Mexico produces data to help alleviate poverty

Written by on October 16, 2017. Posted in Features.

Maize seed samples in CIMMYT's seed bank. CIMMYT/file — Maize (also known as corn) seed samples in CIMMYT’s seed bank. CIMMYT/file

DES MOINES, Iowa (CIMMYT) – Scientist Kevin Pixley holds a large, clear plastic bottle up to the light to illuminate the yellow corn kernels inside. He is leading a project to catalogue 178,000 corn and wheat seeds at the International Maize and Wheat Improvement Center’s (CIMMYT) seed bank near Mexico City.

“The difficulty farmers and researchers face is that no matter how hard they look they can’t see inside a seed to predict its hardiness – they never know whether it will withstand the growing conditions it will experience,” said Pixley, who will speak at the 2017 Borlaug Dialogue symposium in Des Moines, Iowa, on October 18.

CIMMYT’s mission is to apply maize and wheat science for improved livelihoods around the world.

“Our seed bank provides a sub-zero temperature refuge for the largest collection of maize and wheat seeds in the world,” explained Pixley, who leads CIMMYT’s Seeds of Discovery (SeeD) project. “Recent technological advances are accelerating our understanding of the inner workings of these seeds, making them ever more useful to researchers and farmers.

“Through conservation, characterization and use of natural biodiversity, we’re not just helping to improve livelihoods for smallholder farmers in the present, but we’re building our capacity to thwart future threats to food security,” Pixley said. “Every year we ship some 300,000 maize and wheat seed samples to farmers and researchers.”

Through the SeeD partnership between CIMMYT, Mexico’s ministry of agriculture (SAGARPA) and the MasAgro (Sustainable Modernization of Traditional Agriculture) project, scientists are developing the capacity for farmers to prepare for specific or as yet unanticipated needs.

“Seeds of Discovery offers the next generation of Mexican scientists the training and technologies they need to support food security,” said Jorge Armando Narvaez Narvaez, Mexico’s sub-secretary of agriculture.

“In some ways our work has only just begun, but we’re leaps and bounds ahead of where we would be thanks to applying new technologies to secure the food and nutrition needs of our growing population,” Pixley said.

For further information:

Seeds of Discovery video: http://staging.cimmyt.org/seed/

Seeds of Discovery website: http://seedsofdiscovery.org/

Farming First TV: https://www.youtube.com/watch?v=uDwBtWRiHxs

Al Jazeera: Crop Biodiversity the Key to Ending Hunger

For interviews: Julie Mollins, CIMMYT communications j.mollins [at] cgiar [dot] org

Experts call for data revolution to achieve Sustainable Development Goals

Written by on September 25, 2017. Posted in News.

Screen Shot 2017-09-25 at 9.29.22 AM EL BATAN, Mexico (CIMMYT) — Modern data systems are essential to monitor, manage and plan actions taken by governments to achieve the Sustainable Development Goals (SDGs) by 2030, according to the Sustainable Development Solutions Network (SDSN), an advisory body to the United Nations Secretary General, and to the Thematic Research Network on Data and Statistics (TReENDS), an independent group of international experts working on data-related fields.

However, government officials and policy makers around the world are burdened by the challenge of finding reliable data for sustainable development planning, decision making and program design.

To overcome this obstacle public and private institutions must help governments gather, curate, produce, analyze and disseminate information for SDG planning, implementation and assessment, according to a new study by members of the SDSN TReNDS group published recently at the International Conference on Sustainable Development (ICSD).

Counting on the World: Building Modern Data Systems for Sustainable Development, to which the International Maize and Wheat Improvement Center (CIMMYT) contributed as a member of the SDSN TReNDS panel, recommends a collaborative approach based on multi-stakeholder data partnerships to develop modern statistical systems that can provide policy makers with evidence-based information for SDG work.

The report explains the types of data that are needed to plan for sustainable development and offers a roadmap to build 21^st-century data systems to monitor and achieve SDGs. These modern systems are conceived to help governments prepare for and respond to different types of crises, access real-time information for effective action and administration, track progress and adjust course towards the SDGs. Study findings indicate that effective public programs will be the result of informed decision making processes assisted by high-quality, disaggregated and geo-referenced data.

To bring about a data revolution, the report urges governments to invest in education and training, enter into technical partnerships and seek technology exchanges with the private sector to develop statistical capacity. Ultimately, countries should be able to offer high quality data and statistics to public officials, researchers, entrepreneurs and interested citizens by developing such capacity.

In its final section, the report details a roadmap for urgent action that identifies the leading actors who should be responsible for implementing the recommendations and a time frame for reaching concrete results.

Read the full SDSN TReNDS report here.

CSIRO and CIMMYT link on wheat phenomics, physiology and data

Written by Mike Listman on June 26, 2017. Posted in Features.

Building on a more than 40-year-old partnership in crop modelling and physiology, a two-day workshop organized by CIMMYT and Australia’s Commonwealth Scientific and Industrial Research Organisation (CSIRO) achieved critical steps towards a common framework for field phenotyping techniques, data interoperability and sharing experience.

Involving 23 scientists from both organizations and held at El Batán from 12 to 13 June 2017, the event emerged partly from a 2016 visit to CIMMYT by CSIRO Agriculture and Food executives and focused on wheat, according to Matthew Reynolds, CIMMYT wheat physiologist and distinguished scientist.

“Capitalizing on our respective strengths, we developed basic concepts for several collaborations in physiology and breeding, and will follow up within ongoing projects and through pursuit of new funding,” Reynolds said, signaling the following:

Comparison of technologies to estimate key crop traits, including GreenSeeker and hyperspectral images, IR thermometry, digital imagery and LiDAR approaches, while testing and validating prediction of phenotypic traits using UAV (drone) imagery.
Study of major differences between spike and leaf photosynthesis, and attempts to standardize gas exchange between field and controlled environments.
Work with breeders to screen advanced lines for photosynthetic traits in breeding nurseries, including proof of concept to link higher photosynthetic efficiency / performance to biomass accumulation.
Validation/testing of wheat simulation model for efficient use of radiation.
Evaluation of opportunities to provide environment characterization of phenotyping platforms, including systematic field/soil mapping to help design plot and treatment layouts, considering bioassays from aerial images as well as soil characteristics such as pH, salinity, and others.
Testing the heritability of phenotypic expression from parents to their higher-yielding progeny in both Mexico and Australia.
Extraction of new remote sensed traits (e.g., number of heads per plot) from aerial images by machine learning (ML) of scored traits by breeders and use of ML to teach those to the algorithm.
Demonstrating a semantic data framework’s use in identifying specific genotypes for strategic crossing, based on phenotypes.
Exchanging suitable data sets to test the interoperability of available data management tools, focusing on the suitability of the Phenomics Ontology Driven Data (PODD) platform for phenotypic data exchanges, integration, and retrieval.

The shared history of the two organizations in wheat physiology goes back to the hiring by Dr. Norman E. Borlaug, former CIMMYT wheat scientist and Nobel Prize laureate, of post-doctoral fellow Tony Fischer in 1970. Now an Honorary Research Fellow at CSIRO, Fischer served as director of CIMMYT’s global wheat program from 1989 to 1996 and developed important publications on wheat physiology earlier in his career, based on data from research at CIMMYT. In the early 1990s, Lloyd Evans, who established the Canberra Phytotron at CSIRO in the 1970s, served on CIMMYT’s Board of Trustees. Former CIMMYT maize post-doc Scott Chapman left for CSIRO in the mid-1990s but has partnered continuously with the Center on crop modelling and remote sensing. With funding from the Australian Centre for International Agricultural Research (ACIAR) in the late 1990s, CSIRO scientists Richard Richards, Tony Condon, Greg Rebetzke and Graham Farquhar began shared research with Reynolds and Martin van Ginkel, a CIMMYT wheat breeder, on stomatal aperture traits. Following work at CSIRO with Lynne McIntyre and Chapman, scientist Ky Matthews led the CIMMYT Biometrics Group from 2011 to 2012, collaborating with CIMMYT wheat physiologists on a landmark project to map complex physiological traits using the purpose-designed population, Seri/Babax. Reflecting the recent focus on climate resilience traits, Fernanda Dreccer of CSIRO is helping CIMMYT to establish the Heat and Drought Wheat Improvement Consortium (HeDWIC), among other important collaborations.

Breaking Ground: Cesar Petroli on data-driven use of maize genetic diversity

Written by on February 15, 2017. Posted in Features.

Breaking Ground is a regular series featuring staff at CIMMYT

EL BATAN, Mexico (CIMMYT) – Access to genetic data can revolutionize research partnerships and lead to major benefits for crop breeders aiming to help smallholder farmers boost yields, according to Argentinian geneticist Cesar Petroli.

Hailing from Reconquista in Santa Fe Province, Petroli now works for the MasAgro program at the International Maize and Wheat Improvement Center (CIMMYT) and is funded by Mexico’s Ministry of Agriculture (SAGARPA). He first became curious about genetics in the mid-1990s when it was a relatively new field in Argentina and the National University of Misiones offered the only bachelor’s degree in the country. Petroli initially focused on cattle and sheep genetics, which gave him his first introduction to molecular markers, which shed light on characteristics of the organism.

His interest in data and plant genetics took root while he was a student. While completing his doctoral degree at the University of Brasilia in partnership with EMBRAPA, Brazil’s agricultural research body, Petroli began to work on the eucalyptus tree with Diversity Arrays Technology (DArT), an Australian enterprise specializing in developing technologies for whole genome profiling.

At that time, CIMMYT wanted to create what was subsequently to become the Genetic Analysis Service for Agriculture (SAGA) using a platform based on the DArT method. Petroli was the perfect fit. Not only did he bring expertise in sequencing and low-cost DNA fingerprinting, he also brought experience of application of large amounts of data in research; in particular, his experience in eucalyptus.

At the heart of operations at the SAGA laboratory is the Illumina HiSeq 2500 sequencing system, one of only three in Mexico, where CIMMYT is headquartered. Petroli and his team have the capacity to determine the genetic make-up up to 2,500 maize samples per week for both CIMMYT and its partners, generating vast quantities of data in the process.

“We determine the genetic make-up maize and wheat varieties and collections,” Petroli said. “This can help maize breeders to identify patterns in the DNA which are associated with characteristics such as drought and heat tolerance. These patterns or molecular signposts can then be used to help select the best materials for breeding,” he added, explaining that heat and drought resistant maize and wheat varieties not only help present-day farmers, but could also mitigate potential future risks to global food security from the impacts of climate change.

The data generated when fingerprinting thousands of maize and wheat samples provide opportunities for scientific exploration and synergies; while one team may be exploring heat and drought tolerance, another team can use the same DNA fingerprint data to explore other characteristics such as disease tolerance.

“Sharing data for use by interested breeders broadens collaboration and maximizes benefits to smallholder farmers,” Petroli said, describing his enthusiasm for making data publicly available. “Accessible data increases the impact of our research and allows the global public to benefit from the wealth of knowledge we generate.”

In the first six years of the MasAgro program, more than 2 billion genotypic data have been made available in the Germinate and Dataverse platforms. Petroli’s work forms part of bigger efforts at CIMMYT to study and characterize genetic diversity for use in breeding programs.

Big data for development research

Written by on October 27, 2015. Posted in Blogs.

Both private and public sector research organizations must adopt data management strategies that keep up with the advent of big data if we hope to effectively and accurately conduct research. CIMMYT and many other donor-dependent research organizations operate in fund declining environments, and need to make the most of available resources. Data management strategies based on the data lake concept are essential for improved research analysis and greater impact.

We create 2.5 quintillion bytes of data daily–so much that 90% of the data in the world today has been created in the last two years alone. This data comes from everywhere: sensors used to gather climate information, drones taking images of breeding trials, posts on social media sites, cell phone GPS signals, and more, along with traditional data sources such as surveys and field trial records. This data is big data, data characterized by volume, velocity, and variety.

Twentieth century data management strategies focused on ensuring data was made available in standard formats and structures in databases and/or data warehouses–a combination of many different databases across an entire enterprise. The major drawback of the data warehouse concept is the perception that it is too much trouble to put the data into the storage system with too little direct benefit, acting as a disincentive to corporate-level data repositories. The result is that within many organizations, including CIMMYT, not all data is accessible.

Today’s technology and processing tools, such as cloud computing and open-source software (for example, R and Hadoop), have enabled us to harness big data to answer questions that were previously out of reach. However, with this opportunity comes the challenge of developing alternatives to traditional database systems–big data is too big, too fast, or doesn’t fit the old structures.

One alternative storage and retrieval system that can handle big data is the data lake. A data lake is a store-everything approach to big data, and a massive, easily accessible, centralized repository of large volumes of structured and unstructured data.

Advocates of the data lake concept believe any and all data can be captured and stored in a data lake. It allows for more questions and better answers thanks to new IT technologies and ensures flexibility and agility.However, without metadata–data that describes the data we are collecting–and a mechanism to maintain it, data lakes can become data swamps where data is murky, unnavigable, has unknown origins, and is ultimately unreliable. Every subsequent use of data means scientists and researchers start from scratch. Metadata also allows extraction, transformation, and loading (ETL) processes to be developed that retrieve data from operational systems and process it for further analysis.

Metadata and well-defined ETL procedures are essential for a successful data lake. A data lake strategy with metadata and ETL procedures as its cornerstone is essential to maximize data use, re-use and to conduct accurate and impactful analyses.

Maize and wheat global gender study: coding large-scale data to reveal the drivers of agricultural innovation

Written by on March 9, 2015. Posted in News.

Over the last week, MAIZE and WHEAT CRP investigators from the global cross-CRP study on gender in agricultural innovation met at El Batán from 26 Feb to 1 March to take stock of progress so far and plan the next steps in the implementation of this unique research initiative.

From left to right: Patti Petesch, Diana Lopez, Paula Kantor, Vongai Kandiwa, Dina Najjar, Lone Badstue, Anuprita Shukla and Amare Tegbaru. Photo: Xochiquetzal Fonseca/CIMMYT

The study will draw on interviews and focus groups with men and women engaged in small-scale farming around the world, to hear in their words how they practice and innovate in agriculture, and what factors, especially gender relations, they feel have influenced their success and failures. Through rigorous analysis both of the broader patterns in the data and delving deep into the case studies, the aim is to develop strategic research publications as well as practical observations and tools to integrate gender-sensitivity into agricultural research and development.

The appetite for more knowledge about the role of gender was clear at Gender and Development Specialist Paula Kantor’s well-attended brown bag lunch on Friday, introducing the GIZ-funded project on gender constraints to wheat R4D in Afghanistan, Ethiopia and Pakistan.

As CIMMYT Gender Specialist Lone Badstue opened the workshop, she reflected on how quickly gender research has advanced since the CRPs were set up in 2011. From less than one full-time gender-specialist on staff, there are now the equivalent of eight full-time staff working with the CRPs on gender and 20 large projects with gender-integration.

At the workshop, the gender specialists shared their experiences of the 19 case studies conducted under MAIZE and WHEAT so far, before settling down to discuss data quality control and coding.