Use Case Intelligence RSS Search use cases Search
IBM Agriculture global

dsm-firmenich Animal Nutrition & Health

Risk Management

dsm-firmenich needed a more proactive way to identify and predict mycotoxin contamination in feed crops because contamination threatens food safety, animal health, regulatory compliance, and agricultural economics across a large global customer base.

Read the original story Explore all use cases
25% of the world’s crops affected by mycotoxins
61,000 locations around the globe feed the prediction model
about 1 billion metric tons of food and food products lost each year
support to reduce crop losses by a significant amount, saving the agricultural industry millions of euros per year

Reported impact

Business outcome

The service helps feed producers and growers spot contamination risk earlier, target monitoring and mitigation more precisely, reduce crop loss and chemical overuse, and protect food and feed quality with more trustworthy forecasts.

  • Compliance
  • Cost Reduction
  • Risk Reduction

Solution

Researchers at dsm-firmenich Animal Nutrition & Health used IBM Environmental Intelligence Suite to build a predictive mycotoxin-risk service that combines global weather, geospatial, crop, fungal, and occurrence data. The system analyzes hourly weather observations and forecasts extending up to eight months across 61,000 locations, then feeds those conditions into algorithms that account for crop growth stages, fungal life cycles, mycotoxin biochemistry, and historical occurrence data to estimate contamination risk in wheat, corn, soybeans, and other crops. dsm-firmenich also feeds survey and detection-service data back into the models so the forecasts can be refined and tied to recommended mitigation strategies such as earlier testing, altered harvest timing, fungicides, binders, or enzymatic biotransformation. Because the model can produce both regional and farm-specific forecasts, the company turned environmental intelligence into a field-level risk-management workflow that helps partners decide where to monitor more closely and how to reduce loss before contaminated feed enters the supply chain.

Data flow

Hourly weather observations and long-range forecasts from Environmental Intelligence Suite are combined with crop, fungal, and historical mycotoxin occurrence data, scored by prediction algorithms, and returned as regional or farm-level risk forecasts that guide testing, harvesting, and mitigation decisions.

Solution architecture

2 components · 2 layers
  1. Ingest
    • IBM Environmental Intelligence Suite Supplies global weather, forecast, API, analytics, and geospatial inputs for the mycotoxin prediction models.
  2. Serving
    • Mycotoxin prediction Represents the dsm-firmenich predictive service that turns weather and occurrence data into actionable contamination-risk forecasts.

Architecture clues

  • Farm-level predictions are tailored using local factors such as soil tillage, previous crops, and development timing.
  • Survey results feed back into the model to refine predictions and mitigation guidance.
  • The prediction model combines crop stage, fungal lifecycle, mycotoxin biochemistry, occurrence data, and weather inputs.

Evidence from the source

“The FAO estimates that mycotoxins impact 25% of the world’s crops annually, resulting in the loss of approximately 1 billion metric tons of food and food products each year”
“The firm turned to IBM Environmental Intelligence Suite for reliable weather data”
“The mycotoxin prediction models make use of actual hourly weather data—as well as accurate weather forecasts for up to 8 months—from 61,000 different points around the globe”
“These tools now enable real-time mycotoxin contamination prediction and prevention.”
“with accurate and location-specific forecasts, farmers and growers can reduce crop losses by a significant amount”
Transparency Evidence & methodology 90/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    dsm-firmenich Animal Nutrition & Health customer story

    First-party
    https://www.ibm.com/case-studies/dsm-firmenich-anh
    Source type
    Vendor-published customer story
    Published
    Aug 23, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
IBM Apr 6, 2026 United Nations Development Programme Public Sector Global UNDP needed more granular, forward-looking analytics to help governments and development partners decide where clean-energy investments would produce the greatest equity, development, and climate-resilience impact. 1 km resolution Real-time AnalyticsRisk Management IBM Cloud · IBM Environmental Intelligence · IBM watsonx.ai IBM Apr 1, 2026 MyLÚA Health Healthcare United States MyLÚA Health needed an enterprise-ready way to deliver culturally attuned maternal support between appointments while protecting sensitive health information and identifying risk earlier in underserved populations. 48% of participants completed proactive wellness activities Risk Management IBM Cloud · IBM Cloud Code Engine · IBM watsonx Orchestrate IBM Feb 13, 2026 BORICA AD Financial Services Bulgaria BORICA needed to modernize national fraud prevention so it could stop fast, cross-channel attacks in milliseconds without disrupting legitimate payment traffic across multiple banks and service providers. 4,000+ transactions per second Fraud DetectionRisk Management IBM Safer Payments