PxD is building a free weather forecast product for cotton farmers in Pakistan’s Punjab Province to be launched in March, ahead of Kharif – South Asia’s summer planting season. The service will be launched in phases and will ultimately serve 490,000 smallholder cotton farmers across the province.
We are excited by the pioneering potential of this product for distributing weather information to inform decision-making on the part of poor, rural farmers in Pakistan’s cotton belt. Moreover, we have been excited to engage in an intentional process of product design from which we have learned a great deal, and which we anticipate will inform the further iteration and development of weather programming and forecast provision across PxD’s geographies, and beyond.
As we have iterated this new product, we have grappled with wide-ranging design possibilities that could increase usefulness and impact. Guiding questions include: Is it more valuable for farmers to receive good weather information – as is typically offered – or is it more valuable to complement forecast information with digital agronomic recommendations (a core PxD competence)? During what stages of the crop cycle, and for which key decision-points, is weather advisory most valued and impactful? At what frequency should advisory be given? How does one communicate probabilities in a way that is accessible and practical for farmers? How does a farmers’ relationship with the weather – and informational needs – differ based on whether their crops are irrigated or rain-fed?
To guide more informed product design decisions, in November the Pakistan team commenced with a set of end-user interviews with 55 cotton and wheat farmers. While 71% of wheat farmers cited access to weather forecasting information, only 45% of cotton farmers surveyed reported access to weather information. When asked if weather information “helped in planning”, 88 and 86% of cotton and wheat respondents respectively responded in the affirmative. This finding buttresses an earlier survey of wheat farmers users in Pakistan where, in response to the question “What agriculture-related information do you need for your wheat crop during the next month?”, 18.5% of respondents cited weather. When canvassing end-users in November, farmer users were asked to “Please list the types of weather challenges you have experienced” in the three years prior to being surveyed. Forty-three percent of respondents who reported experiencing weather-related challenges cited heavy rainfall and 30% reported high winds.
These types of weather incidents can be very costly for smallholder farmers with limited resources. Inundation washes away expensive inputs, creates mud that blocks sprouting crops, and creates conditions conducive to disease, while wind can destroy or severely damage crops throughout the cropping cycle. Further, when prompted to answer “Out of these weather challenges, which three have the largest impact on your crop costs and yields”, pest management was reported as the most common answer. Many pests and diseases thrive in particular weather conditions and can proliferate quickly if conditions are optimal. This suggests that a combination of advisory and weather forecasting information alerting farmers to be on the lookout for pests and to initiate pesticide application decisions sooner could be valuable as a means for reducing pest damage.
To test certain features of our Kharif forecasting products in practice, the PxD Pakistan team took advantage of the ongoing Rabi wheat season (winter planting cycle) to launch two minimum viable products (MVPs) as an AB test. This round of product development was delivered to roughly 2,000 wheat farmers, with each pilot product servicing approximately 1,000 farmers, respectively. The first treatment entailed a simple 48-hour weather-only forecast delivered via SMS and robocall. The second treatment issued an equivalent 48-hour weather forecast to 1,500 wheat farmers, complemented by recommendations on how to adjust one’s irrigation accordingly.
In February, when users have been exposed to the MVP services for two months, they will be surveyed to obtain richer feedback. This survey will aim to answer the fundamental question about whether farmers value weather-linked advisory over weather-only messages. If weather-only is the clear preference, this may suggest that farmers are generally able to connect actions to relevant weather. In the event that farmers do not explicitly need advisory as a complement to forecasting information, this would greatly simplify product development. Secondary questions source farmers’ views on the frequency and relevance of distributed messages. Lastly, under the hypothesis that farmers will prefer advisory linked to weather information, in-field focus groups will be conducted in March to expose farmers to an array of pre-recorded agronomic recommendations and message framings. Feedback from farmers will be used to inform the iteration of advisory scripts and message framing as we work to maximize comprehension, particularly relating to the communication of uncertainties and probabilities, and address potential barriers to adoption.
Another core challenge in developing this product is the quality of the weather forecasts themselves. The existing forecast services in Punjab tend not to be designed with the end user’s needs in mind. Three services in Punjab, Pakistan exemplify usability issues: the first requires user-initiated, user-paid inbound calls; the second requires internet access; and the third is only available to subscribers of a particular telecoms company.
To overcome these types of challenges, PxD is partnering with the private forecast provider CFAN (Climate Forecast Applications Network) to develop calibrated custom forecasts. CFAN is a leading forecast provider, with temperature, cyclone, and severe weather products across North America, Central America, and Asia, and extensive experience in forecasting South Asia weather dynamics. In addition to giving PxD the flexibility to adapt CFAN’s data streams according to our users’ needs, we are using this partnership to transparently assess the magnitude of upfront costs required to build a forecast system.
Learnings from these research activities, coupled with insights generated by our collaboration with CFAN, will inform the final design of our Kharif weather forecasting product for cotton farmers. Once this product is up and running, the focus will shift to impact evaluation, including pick-up rates, behavior changes, and forecast accuracy. Pending a review of such impact outcomes, and funding considerations, the product will be further developed to cover the Rabi season and potentially scaled to additional countries.
This Kharif season, we are thrilled at the prospect of hundreds of thousands of Punjabi smallholder cotton farmers witnessing less fertilizer – and by implication, fewer resources – washed away or harvests inundated by unexpected rains, deploying more effective irrigation tailored to the forecast, and incurring fewer crop losses due to heavy rains and winds. When we asked our PxD Pakistan agronomist about the potential impact of this product, she said: “This product will reduce farming risks and expenses, and increase what is usually a farmer’s sole source of income – allowing for more investment into farming or money for personal expenses”. We are also excited about the potential for this product to serve as a template for iterative product and design process management, and proof of concept, which others may learn from and implement in other settings.
Mark Tamming is an Associate in the London Office of Oliver Wyman, a management consulting firm. Oliver Wyman generously sponsored Mark in joining PxD as an ‘extern’ for three months on PxD’s product team. Shams Sadiq is a Research Associate on the PxD Pakistan team. We thank Khushbakht Jamal, Mahroz Haider, Jagori Chatterjee, Fatima Fida, Adeel Shafqat, Omer Qasim, Hannah Timmis, and the broader PxD Pakistan team who offered valuable contributions to this post and the product development that sits behind it.