Crop type mapping at the field level is necessary for a variety of applications in agricultural monitoring and food security. As remote sensing imagery continues to increase in spatial and temporal resolution, it is becoming an increasingly powerful raw input from which to create crop type maps. Still, automated crop type mapping remains constrained by a lack of field-level crop labels for training supervised classification models. In this study, we explore the use of random forests transferred across geographic distance and time and unsupervised methods in conjunction with aggregate crop statistics for crop type mapping in the US Midwest, where we simulated the label-poor setting by depriving the models of labels in various states and years. We validated our methodology using available 30 m spatial resolution crop type labels from the US Department of Agriculture's Cropland Data Layer (CDL). Using Google Earth Engine, we computed Fourier transforms (or harmonic regressions) on the time series of LandsatSurface Reflectance and derived vegetation indices, and extracted the coefficients as features for machine learning models. We found that random forests trained on regions and years similar in growing degree days (GDD) transfer to the target region with accuracies consistently exceeding 80%. Accuracies decrease as differences in GDD expand. Unsupervised Gaussian mixture models (GMM) with class labels derived using county-level crop statistics classify crops less consistently but require no field-level labels for training. GMM achieves over 85% accuracy in states with low crop diversity (Illinois, Iowa, Indiana, Nebraska), but performs sometimes no better than random when high crop diversity interferes with clustering (North Dakota, South Dakota, Wisconsin, Michigan). Under the appropriate conditions, these methods offer options for field-resolution crop type mapping in regions around the world with few or no ground labels.
Oil palm expansion resulted in 2 million hectares (Mha) of forest loss globally in 2000–2010. Despite accounting for 24% (4.5 Mha) of the world’s total oil palm cultivated area, expansion dynamics in sub-Saharan Africa have been overlooked. We show that in Southwest Cameroon, a top producing region of Africa, 67% of oil palm expansion from 2000–2015 occurred at the expense of forest. Contrary to the publicized narrative of industrial-scale expansion, most oil palm expansion and associated deforestation is occurring outside large agro-industrial concessions. Expansion and deforestation carried out by non-industrial producers is occurring near low-efficiency informal mills, unconstrained by the location of high-efficiency company-owned mills. These results highlight the key role of a booming informal economic sector in driving rapid land use change. High per capita consumption and rising palm oil demands in sub-Saharan Africa spotlight the need to consider informal economies when identifying regionally relevant sustainability pathways.
Indonesia’s oil palm expansion during the last two decades has resulted in widespread environmental and health damages through land clearing by fire and peat conversion, but it has also contributed to rural poverty alleviation. In this paper, we examine the role that decentralization has played in the process of Indonesia’s oil palm development, particularly among independent smallholder producers. We use primary survey information, along with government documents and statistics, to analyze the institutional dynamics underpinning the sector’s impacts on economic development and the environment. Our analysis focuses on revenue-sharing agreements between district and central governments, district splitting, land title authority, and accountability at individual levels of government. We then assess the role of Indonesia’s Village Law of 2014 in promoting rural development and land clearing by fire. We conclude that both environmental conditionality and positive financial incentives are needed within the Village Law to enhance rural development while minimizing environmental damages.
Our Report draws attention to a complex but understudied issue: How will climate warming alter losses of major food crops to insect pests? Because empirical evidence on plant-insect-climate interactions is scarce and geographically localized, we developed a physiologically based model that incorporates strong and well-established effects of temperature on metabolic rates and on population growth rates. We acknowledged that other factors are involved, but the ones we analyzed are general, robust, and global (1–3).
Parmesan and colleagues argue that our model is overly simplistic and that any general model is premature. They are concerned that our model does not incorporate admittedly idiosyncratic and geographically localized aspects of plant-insect interactions. Some local effects, such as evidence that warmer winters will harm some insects but not others, were in fact evaluated in our sensitivity analyses and shown to be minor (see the Report's Supplementary Materials). Other phenomena, such as plant defenses that benefit some insects and threaten others, are relevant but are neither global nor directional. Furthermore, because Parmesan et al. present no evidence that such idiosyncratic and localized interactions will outweigh the cardinal and universally strong impacts of temperature on populations and on metabolic rates (1–3), their conclusion is subjective.
We agree with Parmesan and colleagues that the question of future crop losses is important and needs further study, that targeted experimental data are needed (as we wrote in our Report), and that our estimates are likely to be conservative (as we concluded, but for reasons different from theirs). However, we strongly disagree with their recommendation to give research priority to gathering localized experimental data. That strategy will only induce a substantial time lag before future crop losses can be addressed.
We draw a lesson from models projecting future climates. Those models lack the “complexity and idiosyncratic nature” of many climate processes, but by building from a few robust principles, they successfully capture the essence of climate patterns and trends (4). Similarly, we hold that the most expeditious and effective way to anticipate crop losses is to develop well-evidenced ecological models and use them to help guide targeted experimental approaches, which can subsequently guide revised ecological models. Experiments and models should be complementary, not sequential.
Reconciling higher freshwater demands with finite freshwater resources remains one of the great policy dilemmas. Given that crop irrigation constitutes 70% of global water extractions, which contributes up to 40% of globally available calories (1), governments often support increases in irrigation efficiency (IE), promoting advanced technologies to improve the “crop per drop.” This provides private benefits to irrigators and is justified, in part, on the premise that increases in IE “save” water for reallocation to other sectors, including cities and the environment. Yet substantial scientific evidence (2) has long shown that increased IE rarely delivers the presumed public-good benefits of increased water availability. Decision-makers typically have not known or understood the importance of basin-scale water accounting or of the behavioral responses of irrigators to subsidies to increase IE. We show that to mitigate global water scarcity, increases in IE must be accompanied by robust water accounting and measurements, a cap on extractions, an assessment of uncertainties, the valuation of trade-offs, and a better understanding of the incentives and behavior of irrigators.
Low-intensity tillage has become more popular among farmers in the United States and many other regions. However, accurate data on when and where low-intensity tillage methods are being used remain scarce, and this scarcity impedes understanding of the factors affecting the adoption and the agronomic or environmental impacts of these practices. In this study, we used composites of satellite imagery from Landsat 5, 7, and 8, and Sentinel-1 in combination with producer data from about 5900 georeferenced fields to train a random forest classifier and generate annual large-scale maps of tillage intensity from 2005 to 2016. We tested different combinations of hyper-parameters using cross-validation, splitting the training and testing data alternatively by field, year, and state to assess the influence of clustering on validation results and evaluate the generalizability of the classification model. We found that the best model was able to map tillage practices across the entire North Central US region at 30 m-resolution with accuracies spanning between 75% and 79%, depending on the validation approach. We also found that although Sentinel-1 provides an independent measure that should be sensitive to surface moisture and roughness, it currently adds relatively little to classification performance beyond what is possible with Landsat. When aggregated to the state level, the satellite estimates of percentage low- and high-intensity tillage agreed well with a USDA survey on tillage practices in 2006 (R2 = 0.55). The satellite data also revealed clear increases in low-intensity tillage area for most counties in the past decade. Overall, the ability to accurately map spatial and temporal patterns in tillage should facilitate further study of this important practice in the United States, as well as other regions with fewer survey-based estimates.
Braun Hall, Stanford University, Stanford, CA 94305
0
gorelick@stanford.edu
gorelick_0.jpg
Professor Gorelick runs the Hydrogeology and Water Resources program and directs the interdisciplinary Global Freshwater Initiative. He is also a Senior Fellow at the Woods Institute for the Environment. Dr. Gorelick is a US National Academy of Engineering (NAE) member and received Fulbright and Guggenheim Fellowships for research on water and oil resources. He is a Fellow of the American Association for the Advancement of Science (AAAS), American Geophysical Union (AGU) and the Geological Society of America (GSA. Dr. Gorelick has produced over 140 journal papers and 3 books in the areas of water management in underdeveloped regions, hydrogeology, optimal remediation design, hydrogeophysics, ecohydrology, and global oil resources.
Increased intake of fruits and vegetables (F&V) is recommended for most populations across the globe. However, the current state of global and regional food systems is such that F&V availability, the production required to sustain them, and consumer food choices are all severely deficient to meet this need. Given the critical state of public health and nutrition worldwide, as well as the fragility of the ecological systems and resources on which they rely, there is a great need for research, investment, and innovation in F&V systems to nourish our global population. Here, we review the challenges that must be addressed in order to expand production and consumption of F&V sustainably and on a global scale. At the conclusion of the workshop, the gathered participants drafted the “Aspen/Keystone Declaration” (see below), which announces the formation of a new “Community of Practice,” whose area of work is described in this position paper. The need for this work is based on a series of premises discussed in detail at the workshop and summarized herein. To surmount these challenges, opportunities are presented for growth and innovation in F&V food systems. The paper is organized into five sections based on primary points of intervention in global F&V systems: (1) research and development, (2) information needs to better inform policy & investment, (3) production (farmers, farming practices, and supply), (4) consumption (availability, access, and demand), and (5) sustainable & equitable F&V food systems and supply chains.
The recently launched Stanford Alumni in Food & Ag group aims to bring together Stanford graduates with a background or interest in food and agriculture issues. Tannis Thorlakson, one of the group’s creators, works as the environmental lead for Driscoll’s in the U.S. and Canada, and recently earned her Ph.D. from Stanford’s E-IPER program. She hopes the group will help alumni stay connected with cutting-edge research and stay up-to-date on news within the food and agriculture space. Thorlakson sat down with FSE to chat about the group and upcoming launch event taking place at the O'Donohue Family Stanford Educational Farm later this month.
Q: What inspired you to create the group and who else was involved? Thorlakson: It has been exciting to see the increasing enthusiasm for agriculture and food around Stanford's campus during my time there. Between the newly expanded Stanford Farm and the buzz around ag tech, more and more students are interested in careers in food and agriculture. My cofounders Manuel Waenke, Anthony Atlas and I wanted to harness some of this enthusiasm to bring alumni together.
Q: Who is eligible to join? Thorlakson: At this point, we are focused only on Stanford alumni, but will build collaborations with student groups over time.
Q: What are your goals or focus areas? Thorlakson: We have two primary goals; to connect alumni to share insights and opportunities in the food and agriculture space; and to keep alumni connected to campus through events and sharing of cutting-edge Stanford research.
Q: You have your first event on Oct. 26. What are you hoping to accomplish, who can come, and how can people learn more? Thorlakson: All alumni and faculty are invited to join. This will be a chance to connect with fellow alumni and learn a bit more about the club. More information here: https://www.stanfordfoodag.com/events.
Q: Anything else you’d like to let others know about? Thorlakson: We're just getting started, so if you have ideas on how to make this group more relevant to you, please reach out to us at mwaenke@stanford.edu.
Walter Falcon, the Helen Farnsworth Professor of International Agricultural Policy in Economics (emeritus), writes from an unusual perspective. During the academic year he serves as a senior fellow with the Freeman Spogli Institute for International Studies and the Stanford Woods Institute for the Environment. He spends the summers on his family farm near Marion, Iowa. He returns to campus each year with reflections on the challenges and rewards of faming life in his "Almanac Report." Falcon is former deputy director of the Center on Food Security and the Environment.
These field notes constitute my seventh summer report from our Iowa farm. As readers of prior postings may remember, my wife and I own a medium-sized farm in east-central Iowa that produces corn, soybeans, and beef from a cow-calf herd. We are fourth-generation custodians of these acres – a long-term family relationship that is typical for many Iowa farms. The atypical dimension of our operation is that I am also a Professor at Stanford University, where I have done research and taught courses on the world food economy for more than 40 years. This contrast in surroundings could not be more stark, which I hope generates field notes of interest to friends at both locations.
The title for this year’s edition is probably redundant. Farmers throughout the world ALWAYS talk about bad weather, low prices, and inept governments. That combination has certainly been front and center this year. The 8 a.m. gathering of farmers at our old Waubeek “restaurant” on the Wapsipinicon River continues to produce interchanges on the latest farm happenings, usually about who or what is to blame for distressed rural conditions.
Trump trade-wars, with farmers as casualties came up frequently in the conversations. There also seemed to be less banter this year and fewer new pick-up trucks.
There has been justifiable concern about the weather, since the 2018 crop year has been strange, even for Iowa. The year began very early, with corn tasseling by Independence Day – completely destroying the old maxim of knee-high by the Fourth of July. Many days of intense heat then occurred during the kernel-filling stage, prompting concerns about low test-weights for the projected harvest. Nevertheless, in late July, both corn and soybeans held prospects for record crops.
Then in August the rain gods became agitated. The local newspaper ran the headline “Rain, Rain, Rain – Heat, Humidity, Tornadoes & Floods.” We received 12 inches of rain in 10 days. Nearby creeks and rivers overflowed; soybeans got driven into the mud from the hard rains and the accompanying high winds; and we dodged a nearby tornado spinning away about four miles from us.
Wet conditions caused white mold and spurred “sudden death syndrome” in some soybean fields – the latter caused by a soil fungus that seems to thrive in damp conditions. Corn ears that had not “fallen” (going from their upright-pointed position on the stalk to the downward position that occurs with maturity) began to collect moisture, creating mildew and ear rot inside the husk. Corn having more than 4 percent damage is very difficult to sell without large price discounts, or to use as cattle feed.
Image
Credit: D. Hogan, example of damaged ear from our farm.
Farmers are also growing increasingly concerned about the added propane costs that will be incurred if corn must be dried before it can be sold. They worry as well that elevators and other shipping points will be “full” because of trade disruptions. Crops that had looked so promising on August 1looked more dubious on September 15.
There is a tendency always to generalize nationally from local conditions, but the prevailing neighborhood view is that the USDA has overestimated the harvest. These conditions have also created considerable discussion about climate change and extreme weather events. For farmers, the concerns are not about climate science, but are much more about risk, farm profitability, and upcoming conversations with bankers.
The weather uncertainty has been compounded by price and trade issues. Soybean prices plunged to a nine-year low, and in mid-September cash prices in rural Iowa markets were about $7.25 per bushel. That level was only about 70 percent of prices in 2013 – even without adjusting for inflation. The soybean supply chain is congested with large stocks in elevators, and uncertainty about the direction of flows is affecting cash prices. Will Midwestern beans go to Pacific ports for shipment to China, as has been the case in recent years, or will they go to Atlantic and Gulf ports for shipment to Europe, as Brazil and the U.S. (partially) exchange customers because of trade disruptions?
At the other end of the crop-price spectrum, hay and straw markets have gone crazy in the opposite direction. Supplies of both are in short supply, largely because of drought in the southern plains and floods in the northern Midwest.
Prices of hay for our cowherd were more than double that of last year, and we also paid dearly – $75 per 3’ x 3’ square bale – for straw that originated in North Dakota! More famers will bale corn stalks for use as bedding this year, but for reasons of nutrients, tilth, and erosion, we are reluctant to remove corn residues from our fields.
The livestock sector also poses a murky outlook for (the typically large) farmers who specialize in raising pigs and/or feeding cattle. Though helped by low feed prices, both the pork and beef sectors are plagued with large numbers of animals on feed, with uncertain exports to China, Mexico, and Europe, and with high prices for replacement animals.
Given the smallness of our cowherd – for us, a cheaper sport than golf – the economic consequences are not overly severe. Even so, we are looking at a great calf crop, the prize of which is “my” shorthorn steer calf shown below. “My” is used advisedly, since my wife would prefer that our herd be Angus, whereas my family’s tradition was with Shorthorns. I was in special trouble, therefore, when, during my Stanford absence, my wife and a neighbor had to pull this particular calf in the middle of the night in a driving rainstorm. As for the herd more generally, we have compromised. Half are Shorthorn and half are Angus, and this year my wife won the tiebreaker – our herd bull is mostly Angus. He is massive, fitting his name “Samson,” and he is both a pet and a pest. He is trained to lead, likes people, knows his name, and sometimes behaves like a kitten. Unfortunately, his well-intentioned shoulder nudges can send one sailing.
Credit: L. Harney: “Hogie” at two months.
Credit: L. Harney, “Hogie” at two months.
The implications of commodity prices on land prices are still uncertain as very little cropland is being offered for sale. But negotiations on cash rents are much more contentious this year. There is quite clear evidence that cash rents, many of which were in the $275-$300 per acre range only a couple of years ago, have come down by 20 percent.
This somewhat dismal rural outlook sets the scene for the upcoming midterm elections. Iowa voted for Trump in 2016, where he ran very strongly in rural areas. As an “outside-insider” (especially from California!) it has been especially challenging for me to read the current political attitudes of farmers. They do not talk politics very openly, so I first looked at what was happening at the Iowa State Fair.
Even without the obvious political overlay, the fair was spectacular. It attracted more than a million visitors – remarkable given that Iowa has only 3.1 million people in total. The traditional cow, sculpted in 600 pounds of butter, stood alongside a butter version of a “1919 Waterloo Boy,” a forerunner to John Deere tractors.
Then there was also the new culinary treat – pork belly with brown sugar on a stick. This specialty was complemented by a demonstration of foot-stomping wine making. Not surprisingly, I drew MUCH anti-California ire when I suggested that this process might actually improve the quality of Iowa wine. And of course there was superbull (3,030 pounds) and superboar (1,165 pounds)!
Credit: Iowa State Fair, butter sculpture of Jersey cow and1919 tractor.
What was most notable, at least to me, was the fair’s political overtone – “corn dogs with a side of politics” noted one local pundit. There was lots of campaigning for state-level offices, and also for the races for the U.S. House of Representatives. At the national level, one would have thought it was 2020. Presidential hopefuls showed up in large numbers. One candidate known by almost no one, John Delaney, had already visited all 99 Iowa counties – a “full Grassley,” named after Iowa’s long-term Senator who has made 38 annual visits to all 99 counties an integral part of his political strategy.
The question that I most hear from my liberal California friends concerns buyer’s remorse. Their assumption is that with tariffs, trade, turmoil, and Trump, farmers must be up in arms and ready to change their political allegiance. My conjecture is that many are not changing – at least not yet – and that the reasons are complicated.
Iowa’s population is now more than 90 percent white, with the farmer percentage even higher. Many farmers, and especially rural women, do not care for Trump or his shaky moral compass; however they are not resonating to Democratic minority messaging either. They like tax cuts, and especially the prospects of E15 ethanol that the president and secretary of agriculture have been dangling in front of them.
Soybean farmers might seem to have the most to complain about as a result of the Chinese imposition of retaliatory tariffs on U.S. soybeans as part of the ongoing trade war. Soybean exports to China through July 2018 were down more that 50 percent as compared to last year. On the other hand, the value of total soybean exports was off by only 8 percent as a consequence of substituting customers among U. S., Brazilian, and other exporters.
I also sense two other related points. First, farmers seem to be assuming (hoping?) that the trade war will be a matter of months not years. Second, many have not yet “priced” (hedged or sold for forward delivery) much of the current year’s soybean crop. In that sense, the tariff/trade impacts have yet to hit home. When they do, political views may change. Interestingly, the bulk of the soybean harvest will occur just a month before the mid-term elections.
Government policy is also at work. While all of the key farm organizations are on record as preferring trade to subsidies, farmers will certainly cash government checks! Under a supplemental program announced by the president (some would say cynically as an election-year “sweetener” for his wrong-headed tariff policy), soybean farmers with yields of 50 bushels per acre will receive a special bonus of about $40 per acre.
Finally, crop insurance serves as a safety net. More than 90 percent of Iowa soybean farmers purchase 80 percent, revenue-guaranteed insurance. This insurance contains key price and yield details, but basically, farmers are compensated for any gross-revenue losses – whether caused by yields or prices – of greater than 20 percent as compared to what they received in 2017.
Whatever one may think about farmer political preferences, the economics of their changing that support is much more complicated than first meets the eye. My conclusion is that Iowa will continue to be a fierce battleground state, and that neither Republicans nor Democrats can take Iowa for granted in either 2018 or 2020.
Iowa is not exactly a major tourist destination. With a few exceptions, like the state fair and the bike ride across Iowa (RAGBRAI) where 20,000 bicyclists (willingly!) ride 450 miles in the summer heat from the Missouri River on the west to the Mississippi River on the east, the common view is that not much happens here.
When my wife and I were growing up, “tourism” meant going for short Sunday drives. Mostly these trips were for the purpose of our fathers comparing the straightness of neighbors’ cornrows. And there were always “Sauerkraut Days” in the town of Lisbon, “Pickle Days” in Walker, plus all of the church-sponsored ice cream socials and dinners.
Then as now, however, Iowa is dotted with interesting historical communities, especially the Amish who settled in Iowa during the last half of the 19thcentury. We have restarted the short-drive tradition, and one of the more interesting visits was to Hopkington, an Amish community just to our north. The devout members of the community do not believe in motors or electricity, and the local scenes are very bucolic: large white houses, not electrified, for their typically large families; horse-drawn farming implements and horse-drawn buggies tied up in neat rows at the church; women in long skirts and bonnets and men with bib-overalls and wide brimmed hats; and wonderful baked goods, cheeses, quilts, and other specialties for sale at roadside stands.
Credit: R. Naylor, Amish buggy and roofers at work.
Horse sales are big events in these communities, with both draft and driving horses featured at auction. Truth in advertising seems to be the order of the day – though I confess some of the descriptions had me thinking of Washington, D. C. For example, an eight-year old draft horse –“pulls hard from either the right or left side”, and a three-year old gelding – “leads real well, but needs more time on the buggy.”
The Amish are struggling with the 21stcentury. Finding enough farmland, in keeping with their tradition of providing all sons with space to farm, is causing some of these communities to break apart. The correct type of schooling is also an issue. And adapting religious norms raises both questions and eyebrows.
It is interesting that a high percentage of all of the roofing of barns and other farm buildings in the entire region is done by Amish men. But how do they get to job sites? If it is too far to drive their horses, they now deem it acceptable to ride in autos with others, so long as they do not drive. A friend of ours is essentially the “Uber-driver” for the Amish roofers of Hopkington. It is interesting, in Iowa and the entire world, what happens when economics and religion clash.
For someone whose day job has been teaching risk analysis and the world food economy, being in Iowa during the summer of 2018 was like living in a 24/7 laboratory. I hope that this experience has given me both the inspiration and ammunition to keep ahead of a fresh batch of bright Stanford students, many of whom have never been on a farm. I will soon know – classes begin this week.
Credit: L. Harney: “Hogie” at two months.
