How Commodity Forecasting Can Pay for Your Sustainability Initiatives

The same data that anticipates and mitigates price fluctuations can protect and enhance your environmental reputation

*The following is an excerpt from a new white paper available from Descartes Labs.*

Overview

Executives in commodity-intensive industries face many challenges today. Not only do they have to improve supply chain efficiencies in the fight against margin compression and increasing competition from algorithmic traders, but they also have to prove to concerned stakeholders and constituencies that they’re truly committed to taking care of the environment.

While these two challenges may seem at odds with each other, they can both be overcome with a data-driven solution proven to reduce procurement costs for manufacturers by 2–4%. Those savings, which are typically in the $3–5 million range and generated from intelligent hedging decisions, can then be used to help firms meet Net Zero commitments, prevent deforestation, and comply with soon-to-be-enforced government regulations.

In this paper, we’ll explain the benefits of using proprietary, customizable datasets from satellites, weather, AIS, market data, and other diverse sensors to make better commodity forecasting decisions. At the same time, we’ll demonstrate how those datasets can kickstart sustainability efforts that protect the planet, keep businesses in compliance, and make it easier to attract and retain customers, investors, and employees.

Key takeaway: Supply chain optimization and sustainability are inextricably linked and can both be addressed with a single solution that reduces costs, as well as environmental impact.

Machine learning combines agronomic and weather data to predict palm oil production. This model uses many of the same datasets critical to accurate deforestation and forest carbon loss estimates.

Geospatial Knowledge Is Power

While agri-business wrestles with economic and environmental issues, vast amounts of data about the Earth and its resources can provide powerful solutions. External data collected from satellites, weather, AIS, market data, and other diverse sensors — especially when combined with internal data from transactions, markets, ERP systems, and other sources — can help business leaders develop sourcing and sustainability strategies that ensure greater profitability with reduced environmental impact.

By monitoring weather, acreage, energy prices, transportation systems, port congestion, and other factors, companies can gain a complete, planetary-scale analysis of current and future market and environmental conditions.

“Geospatial data breaks down the world’s complexity in measurable ways,” says Erika Randolph, Director of Sustainability at Descartes Labs. “Large agri-food companies rely on the data we provide about land use and weather patterns to illuminate previously opaque supply chains and forecast commodity market prices. They save millions on purchasing, and get the added benefit of achieving important sustainability goals faster.”

Accurate commodity maps, forest carbon, and weather data contribute to a geospatially informed supply chain.

Using Geospatial Data to Cut Costs

Geospatial data has been demonstrated to help companies derive more value from trading and procurement processes. Typical margin increases of between 2% and 4% of total procurement costs are achieved by using the data to make more informed decisions that reduce risk, resulting in a geospatial data solution ROI of up to 20X.

Let’s take market forecasting of crude palm oil as an example. Models generated by Descartes Labs use publicly available macroeconomic and market data, such as prices, market participant positions, inflation, etc., along with geospatial data that provides insights into fundamentals like Malaysian Palm Oil Board (MPOB) production, stocks and exports, acreage over time, temperature and precipitation, impact on yield, and more.

“The models update daily and predict prices for multiple time horizons, ranging from two weeks to six months and beyond, forecasting various contracts on the curve with average directional accuracy percentages in the mid-to-high 60s,” says Eduardo Franco, Head of Market Forecasting at Descartes Labs. “Using an intelligent hedging strategy, this enables futures purchasing savings of 4.5% or more over existing benchmarks.”

For companies with unique business requirements, modifications can easily be made to existing forecasting models, such as adding data from proprietary sources, changing reporting timeframes, and allowing for different price-setting mechanisms, geographies, calendars, and growing seasons. Models and strategies are configured to meet every customer’s business requirements and incorporate any customer proprietary data that enhances performance and ensures uniqueness for each deployment.

Currently, Descartes Labs offers forecasting models for palm oil, sugar, and soybean meal futures. Models for coffee, cocoa, corn, and soybean oil futures are coming soon, along with cash market models for select oils and fats.

Vegetation indices confirm damage to sugar production and support elevated price levels.

The Inevitability of Sustainability

While about 30% of Fortune Global 500 companies have voluntarily made commitments to become carbon neutral and/or achieve Net-Zero emissions targets, it’s apparent that new regulations will compel firms to achieve these goals in the very near future. Companies doing business in the EU, for example, will likely be faced with new anti-deforestation and traceability standards in late 2021 or early 2022.

Firms that deal in agriculture, forestry, and other land use (AFOLU) are under more intensive scrutiny because the single sector accounts for 23% of global greenhouse gas (GHG) emissions. Fortunately, steps can be taken by industry players to actually solve more of the problem than what stems from supply chains. Through activities such as reducing deforestation, promoting agroforestry, and using regenerative agricultural practices to sequester carbon in the soil, the AFOLU sector can contribute an estimated 30% of the emission reductions and carbon sequestration necessary to achieve the stated goal of a 1.5-degree-Celsius world (1).

Source: IPCC, 2019 (2)

In addition to complying with regulatory requirements, companies that embrace environmental, social, and governance (ESG) initiatives early will get on the fast track to continuous competitive advantage among consumers and employees alike. 67% of millennials — the largest generation in the workforce — won’t work at companies without established sustainability initiatives, and 70% of millennials consider a company’s environmental focus before making a purchase (3).

Using Geospatial Data for Environmental Stewardship

Imagine a forested landscape that supplies several palm oil mills in Malaysia. The region likely includes areas of natural forest, industrial plantations, and “smallholder” plots in between that make “No Deforestation, No Peat, and No Exploitation” (NDPE) compliance more challenging.

AFOLU companies need to understand probable source locations, land-use histories, and aggregate sourcing practices for each mill in their supply chain. They also need to attribute ongoing deforestation activity to specific mills and suppliers to enable grievance response.

However, no widely available information exists that traces palm throughout the supply chain or directly attributes palm harvested within a plantation to the mill that eventually processes it. Further, concession ownership and permits have little transparency, making it challenging to attribute deforestation to specific growers.

Still, there are a few factors that bind the sourcing region for a given palm mill (e.g. distance, transportation network, mill capacity, nearby mill capacity, etc.) that allow us to estimate the probability and risk of a given mill processing palm from a given plantation. The ability to capture this information as geospatial data and review it within an analytical platform enables sustainability managers to build a digital twin of the supply chain and answer key questions through ongoing monitoring and predictive analytics.

The same geospatial datasets that help with palm oil market forecasting can put businesses on a surer path to sustainability. For example, companies integrate our palm masks with weather data to estimate acreage and yield for market forecasting and use those same masks as inputs to calculate deforested acreage near each mill and estimate the amount of carbon lost. By calculating mill-level deforestation and carbon risk scores across Malaysia and Indonesia, companies can verify sustainable sourcing commitments and provide tools to help non-compliant participants adopt more Earth-friendly practices…

You can read the rest of the white paper by downloading it at this link. Or contact us directly to learn how we can help you build a more geospatially informed supply chain.

References:

1. Yakupitiyage, Tharanga. “Q&A: 17 Percent of the Problem, but 30 Percent of the Solution.” Inter Press Service, 18 Jan. 2019
2. IPCC, 2019: Climate Change and Land: an IPCC special report on climate change, desertification, land degradation, sustainable land management, food security, and greenhouse gas fluxes in terrestrial ecosystems [P.R. Shukla, J. Skea, E. Calvo Buendia, V. Masson-Del- motte, H.-O. Pörtner, D. C. Roberts, P. Zhai, R. Slade, S. Connors, R. van Diemen, M. Ferrat, E. Haughey, S. Luz, S. Neogi, M. Pathak, J. Petzold,J. Portugal Pereira, P. Vyas, E. Huntley, K. Kissick, M. Belkacemi, J. Malley, (eds.)]. In press.
3. Best, Elisabeth and Mitchell, Nikita, ”Millennials, Gen Z, and the Future of Sustainability.” BSR, October 24, 2018.